© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39823
    Prev
    Next
    INDEX
    Explanations

    CSS styles, comments, and code constructs

    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_3_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
    0.93
     I
    0.81
    ao
    0.79
    le
    0.78
    Ä
    0.77
    ó
    0.75
     l
    0.75
    ors
    0.72
    8
    0.72
     T
    0.71
    POSITIVE LOGITS
    ти
    0.95
    انات
    0.81
    '});
    0.72
    ناك
    0.70
    *',
    0.70
    上方
    0.69
    dé
    0.68
    nienia
    0.68
    ]){
    0.68
    alya
    0.68
    Activations Density 0.001%

    No Known Activations