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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103822
    Prev
    Next
    INDEX
    Explanations

    suit, clothing, or suitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    ,
    1.42
    el
    1.39
    as
    1.31
    x
    1.26
    in
    1.15
    on
    1.13
    ar
    1.12
     I
    1.07
    ↵
    1.04
    er
    1.01
    POSITIVE LOGITS
     بتوان
    0.93
     می‌کن
    0.93
    くない
    0.92
    ϲ
    0.91
     بیش
    0.88
     دیکھا
    0.85
    ！)
    0.85
    ⅽ
    0.85
     risposta
    0.84
     मिळाली
    0.84
    Activations Density 0.001%

    No Known Activations