© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35006
    Prev
    Next
    INDEX
    Explanations

    refusing to

    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_11_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
    о
    0.66
    g
    0.61
    ă
    0.58
    декс
    0.56
    ائ
    0.56
     ㅇ
    0.55
    堣
    0.55
    ների
    0.54
    ীদার
    0.54
    ంట్
    0.54
    POSITIVE LOGITS
    lowing
    0.69
    (
    0.65
     curation
    0.63
    follow
    0.61
     하게
    0.60
    也好
    0.59
     contagious
    0.58
    going
    0.57
     प्रमाण
    0.57
    ทำ
    0.57
    Activations Density 0.003%

    No Known Activations