© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78471
    Prev
    Next
    INDEX
    Explanations

    attention mechanism

    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_0_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
     in
    2.09
     for
    1.54
    在
    1.54
    ials
    1.47
    \
    1.45
    _
    1.27
    uting
    1.22
    もら
    1.22
    (
    1.22
     of
    1.20
    POSITIVE LOGITS
    is
    1.89
    ра
    1.59
     to
    1.57
    я
    1.52
    ו
    1.51
    an
    1.42
    ia
    1.37
    지
    1.30
    ে
    1.29
    ید
    1.28
    Activations Density 0.004%

    No Known Activations