© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1157
    Prev
    Next
    INDEX
    Explanations

    towns and villages

    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_39_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
    廡
    0.42
     चिंग
    0.40
     maîtres
    0.40
     बोर
    0.40
     Buck
    0.39
     Ayn
    0.38
    MovementControls
    0.38
     Arundel
    0.38
     Melville
    0.38
    டுகளில்
    0.38
    POSITIVE LOGITS
     village
    0.64
     અમદાવાદ
    0.54
     कोलकाता
    0.53
    村
    0.53
     서울
    0.52
    广州
    0.52
    杭州
    0.51
    village
    0.49
     சென்னைய
    0.48
     ಬೆಂಗಳ
    0.47
    Activations Density 0.052%

    No Known Activations