© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214870
    Prev
    Next
    INDEX
    Explanations

    return jsonify

    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_31_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
    ບໍລິ
    0.41
    投
    0.39
    investment
    0.37
     reluctantly
    0.36
     vlá
    0.36
     ядра
    0.36
     devolver
    0.36
     liné
    0.36
    utin
    0.35
    inear
    0.35
    POSITIVE LOGITS
    韦
    0.36
    "))
    0.36
    ជាក់
    0.35
     diameter
    0.35
    abbam
    0.34
    xmlns
    0.34
    ハー
    0.34
     packaging
    0.34
    ジア
    0.34
     Lifting
    0.34
    Activations Density 0.002%

    No Known Activations