© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5997
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_39_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
     Lipschitz
    0.39
    ষ
    0.38
    shaded
    0.36
    spě
    0.36
    pped
    0.36
     cordova
    0.36
    وازي
    0.36
     sets
    0.35
    ት
    0.35
     Sets
    0.35
    POSITIVE LOGITS
    デュー
    0.45
     dew
    0.42
    މ
    0.40
    லும்
    0.39
    rums
    0.38
    Dylan
    0.38
    Dew
    0.37
    getNum
    0.37
    num
    0.37
     lagoons
    0.37
    Activations Density 0.489%

    No Known Activations