© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82231
    Prev
    Next
    INDEX
    Explanations

    zotero, vicuna, gjirokaster, kobo, .gov, .urls with specific domain endings

    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_0_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
    在
    0.84
    ও
    0.79
    هاي
    0.75
    도
    0.75
     في
    0.73
     మరియు
    0.69
     in
    0.69
    もら
    0.68
    も
    0.66
    면
    0.66
    POSITIVE LOGITS
    t
    1.63
    -
    1.23
     can
    1.17
     are
    1.16
    <
    1.09
     was
    1.05
    ",
    1.02
     is
    0.99
     the
    0.96
    ?
    0.96
    Activations Density 0.047%

    No Known Activations