© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23947
    Prev
    Next
    INDEX
    Explanations

    C

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    جلد
    0.40
     perfekte
    0.38
    मंत्र
    0.38
    hmann
    0.38
    Հ
    0.38
     الجلد
    0.38
    гідно
    0.37
     डिलिव
    0.37
    hoed
    0.37
     आरा
    0.37
    POSITIVE LOGITS
    ycz
    0.43
    низ
    0.38
    <unused46>
    0.35
    ctic
    0.35
    riba
    0.34
    ule
    0.34
    istir
    0.34
     programming
    0.34
     Repar
    0.34
     Regina
    0.33
    Activations Density 0.012%

    No Known Activations