© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46728
    Prev
    Next
    INDEX
    Explanations

    color codes

    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_10_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
     teori
    0.76
     Dijk
    0.62
    FindingsResponse
    0.62
     maca
    0.60
     */
    0.59
     Domains
    0.59
    ER
    0.58
     Dole
    0.58
     BVHTree
    0.58
     Rohit
    0.57
    POSITIVE LOGITS
    א
    0.77
    <0x80>
    0.75
    $
    0.61
    ilor
    0.60
     불구하고
    0.58
    é
    0.57
    itter
    0.55
    '
    0.54
    $",
    0.54
    á
    0.54
    Activations Density 0.004%

    No Known Activations