© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136011
    Prev
    Next
    INDEX
    Explanations

    Zenmoney

    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_12_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
    لف
    0.59
    л
    0.59
    క్
    0.58
    الم
    0.56
     μόνο
    0.55
    ши
    0.54
    J
    0.54
    وم
    0.53
    for
    0.53
    ({
    0.53
    POSITIVE LOGITS
     Russians
    0.54
     Acids
    0.52
     attracts
    0.52
     Russian
    0.52
     EN
    0.50
     Colgate
    0.50
     Louise
    0.49
     cyclical
    0.49
     Russia
    0.49
     Lisa
    0.49
    Activations Density 0.000%

    No Known Activations