© 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. 40857
    Prev
    Next
    INDEX
    Explanations

    `all`, `customer`, `sir`, `port`

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    0.88
    {
    0.74
    i
    0.65
    ក្រោម
    0.62
    o
    0.62
    м
    0.62
    "].
    0.61
    не
    0.58
    سى
    0.57
    ++;
    0.57
    POSITIVE LOGITS
    의
    0.77
    ные
    0.72
     স্থানীয়
    0.72
     बढ़ते
    0.70
     गाड़ियों
    0.69
    nya
    0.67
    न
    0.67
    मेलन
    0.66
    の
    0.65
    ದ್ದ
    0.65
    Activations Density 0.018%

    No Known Activations