© 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. 29239
    Prev
    Next
    INDEX
    Explanations

    and so on

    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
    ůli
    0.85
    ertian
    0.74
    responder
    0.67
     unbear
    0.67
    lective
    0.66
    狲
    0.66
    otheby
    0.65
    qid
    0.65
    flamingo
    0.64
    issions
    0.63
    POSITIVE LOGITS
    t
    1.20
    w
    0.97
    ی
    0.93
    s
    0.91
    c
    0.91
    ?
    0.90
    ח
    0.89
    ي
    0.88
    א
    0.84
    ק
    0.83
    Activations Density 0.001%

    No Known Activations