© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103741
    Prev
    Next
    INDEX
    Explanations

    texture

    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_1_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
    IS
    1.08
    ;
    1.01
    V
    0.96
    Т
    0.95
    З
    0.93
    X
    0.93
    Q
    0.91
    ଭ
    0.87
    J
    0.86
    С
    0.86
    POSITIVE LOGITS
    s
    1.11
    in
    1.08
    at
    1.06
    o
    0.92
    et
    0.87
    с
    0.84
    то
    0.76
    os
    0.76
    ())
    0.73
    us
    0.71
    Activations Density 0.001%

    No Known Activations