© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102771
    Prev
    Next
    INDEX
    Explanations

    php code blocks

    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_1_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
     for
    1.25
    ě
    1.09
     abon
    1.01
    য়া
    0.97
    أ
    0.95
    لي
    0.95
     bushes
    0.93
     astron
    0.93
    数据集
    0.93
    iru
    0.92
    POSITIVE LOGITS
    that
    1.09
    ↵↵
    1.08
    to
    0.89
    table
    0.86
    dan
    0.86
    defines
    0.86
    deterministic
    0.84
    р
    0.84
    data
    0.83
    topic
    0.82
    Activations Density 0.000%

    No Known Activations