AI RESEARCH
A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs
arXiv CS.CL
•
ArXi:2603.26236v1 Announce Type: new While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process culture-specific pragmatic registers, such as slang, as isolated language-specific memorizations or as unified, abstract concepts. We study this by probing the internal representations of Gemma-2-9B-IT using Sparse Autoencoders (SAEs) across three typologically diverse source languages: English, Hebrew, and Russian. To definitively isolate pragmatic register processing from trivial lexical sensitivity, we.