© 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. 85361
    Prev
    Next
    INDEX
    Explanations

    code following "you"

    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
    ：（
    0.82
     trycatch
    0.73
    ir
    0.73
    この
    0.72
    （
    0.72
     for
    0.69
    لاك
    0.68
    /****
    0.67
    ！（
    0.67
     （
    0.66
    POSITIVE LOGITS
     .
    1.03
    ב
    0.94
    ne
    0.91
    ς
    0.87
     on
    0.82
    ง
    0.78
    ъ
    0.76
    л
    0.75
    .).
    0.73
    ität
    0.73
    Activations Density 0.004%

    No Known Activations