© 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. 128920
    Prev
    Next
    INDEX
    Explanations

    toolbox filled with components

    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
    <0xBB>
    0.96
    ي
    0.93
    м
    0.91
    𝟯
    0.87
    夶
    0.87
     красо
    0.85
    bö
    0.85
    now
    0.84
    ра
    0.84
    springen
    0.83
    POSITIVE LOGITS
    us
    1.33
    ac
    0.98
    a
    0.97
    ade
    0.97
    ਰ
    0.97
    ва
    0.96
    </h2>
    0.95
    h
    0.95
    ore
    0.91
     after
    0.90
    Activations Density 0.000%

    No Known Activations