© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201938
    Prev
    Next
    INDEX
    Explanations

    sheaf theory, vector bundles, coefficients

    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_12_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
    нето
    0.57
    ﹊
    0.51
    ;$
    0.50
    Bai
    0.49
    のひとつ
    0.49
    sustainable
    0.49
    Sustainable
    0.49
    (--
    0.48
    Feng
    0.48
    例文帳に追加
    0.48
    POSITIVE LOGITS
     شي
    0.55
     predicts
    0.52
     Spit
    0.50
     పార్
    0.50
     би
    0.49
     parl
    0.49
     predict
    0.49
     пред
    0.49
     قال
    0.48
    ẫ
    0.48
    Activations Density 0.000%

    No Known Activations