© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108254
    Prev
    Next
    INDEX
    Explanations

    styrene, booty, styptic

    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_2_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
    an
    1.63
    in
    1.26
    ان
    1.20
    ar
    1.20
    リ
    1.04
    I
    0.97
    ach
    0.96
    en
    0.95
    et
    0.95
    on
    0.93
    POSITIVE LOGITS
    '
    1.23
    d
    1.09
    x
    0.98
    是因為
    0.96
    ne
    0.92
    ۔
    0.91
    މ
    0.88
    ני
    0.87
    .
    0.86
    Від
    0.83
    Activations Density 0.001%

    No Known Activations