© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161411
    Prev
    Next
    INDEX
    Explanations

    percentage and fraction calculations

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ＮＡＮＡ
    0.39
     teenager
    0.37
     motorbike
    0.37
    विदा
    0.36
     stocked
    0.36
    芜
    0.35
    ロボ
    0.35
     REQUI
    0.34
    ধিক
    0.34
    替え
    0.34
    POSITIVE LOGITS
     rh
    0.38
    QFont
    0.38
     অধি
    0.36
    markup
    0.36
    вающий
    0.35
    bate
    0.34
    court
    0.34
    gente
    0.34
     کھلاڑی
    0.34
    뜹
    0.33
    Activations Density 0.000%

    No Known Activations