© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33665
    Prev
    Next
    INDEX
    Explanations

    -ification and -ism endings

    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_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
    '
    0.82
     I
    0.75
    定的
    0.60
    at
    0.59
    <0xA3>
    0.57
     выполнения
    0.57
    to
    0.56
    ，
    0.55
    ิ
    0.54
     regist
    0.53
    POSITIVE LOGITS
    ی
    0.95
    ים
    0.85
    s
    0.79
    DC
    0.74
    in
    0.73
    ES
    0.73
    SM
    0.72
    ት
    0.72
    CH
    0.71
    データ
    0.69
    Activations Density 0.003%

    No Known Activations