© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6152
    Prev
    Next
    INDEX
    Explanations

    lmsys Vicuna

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    su
    1.17
    蝟
    1.13
    騒
    1.12
     ͡
    1.11
     लढ
    1.09
    会有
    1.09
    тал
    1.08
    ্ঞ
    1.08
    甴
    1.07
    kanı
    1.07
    POSITIVE LOGITS
    as
    2.06
    asd
    1.57
    র
    1.50
     Wordsworth
    1.31
    াল
    1.31
    स्थल
    1.30
     заход
    1.29
    ﻩ
    1.26
    ю
    1.24
    en
    1.23
    Activations Density 0.056%

    No Known Activations