© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124147
    Prev
    Next
    INDEX
    Explanations

    names Scott, Camp, Baum, Te, city

    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_3_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
     be
    0.77
    ،
    0.71
     och
    0.64
     an
    0.62
    ੇ
    0.61
    的
    0.59
    of
    0.58
    ，
    0.58
    be
    0.55
    는
    0.55
    POSITIVE LOGITS
    ताओं
    0.69
    ,_-
    0.66
    u
    0.66
    at
    0.64
    ../
    0.64
    이지만
    0.63
    이었
    0.63
    AH
    0.61
    .//
    0.61
    uq
    0.61
    Activations Density 0.000%

    No Known Activations