© 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. 130085
    Prev
    Next
    INDEX
    Explanations

    g(x) function notation

    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
    ка
    1.60
     a
    1.46
    AN
    1.12
    ك
    1.10
    IN
    1.07
    на
    1.05
    (
    1.04
    IS
    1.02
    IR
    1.01
    ус
    1.01
    POSITIVE LOGITS
    ip
    1.18
    v
    1.16
    st
    1.12
    ре
    1.00
     on
    0.95
    b
    0.94
    f
    0.93
    z
    0.91
    et
    0.89
    ↵
    0.87
    Activations Density 0.001%

    No Known Activations