© 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. 50097
    Prev
    Next
    INDEX
    Explanations

    lists of languages

    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
     се
    0.53
    Б
    0.52
    蒂
    0.51
    名は
    0.50
    点头
    0.49
     pontos
    0.47
    椀
    0.46
     relatos
    0.46
     الفترة
    0.46
    Т
    0.46
    POSITIVE LOGITS
    green
    0.58
    fried
    0.55
    <\
    0.52
    fords
    0.52
    key
    0.50
     Einen
    0.50
    sell
    0.49
    ground
    0.48
    password
    0.48
    gap
    0.48
    Activations Density 0.000%

    No Known Activations