© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39513
    Prev
    Next
    INDEX
    Explanations

    explaining a reason

    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_11_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
    st
    0.84
    de
    0.68
    int
    0.67
    from
    0.67
    fish
    0.63
    for
    0.62
    ing
    0.61
    f
    0.61
    get
    0.60
    too
    0.60
    POSITIVE LOGITS
     ở
    0.73
    嵃
    0.69
    枻
    0.67
     instinctive
    0.63
     Ở
    0.62
     πρώτη
    0.61
    പരമായ
    0.61
     Tecnologia
    0.61
     социальной
    0.61
     pisan
    0.61
    Activations Density 0.000%

    No Known Activations