© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226675
    Prev
    Next
    INDEX
    Explanations

    inflammatory diet, URLs, sasan, operating loss, speeches

    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_10_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
    路
    0.63
    The
    0.62
    Question
    0.61
    in
    0.61
    Institution
    0.58
    Image
    0.57
    Blood
    0.54
    </h3>
    0.54
     CDA
    0.53
    It
    0.53
    POSITIVE LOGITS
     vivir
    0.62
    ۵
    0.62
    ول
    0.61
     española
    0.59
     powied
    0.59
     fabricación
    0.58
     pelea
    0.58
     nostru
    0.58
    akar
    0.57
     кораб
    0.57
    Activations Density 0.000%

    No Known Activations