© 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. 107559
    Prev
    Next
    INDEX
    Explanations

    sack of

    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
    大
    1.38
    .
    1.27
    is
    1.26
    on
    1.25
    ments
    1.23
    at
    1.23
    in
    1.22
    一
    1.00
    for
    0.98
    ak
    0.97
    POSITIVE LOGITS
     (
    1.42
    ર
    1.27
     were
    1.16
    ر
    1.13
    ত
    1.10
    장
    1.10
    ض
    1.08
    ס
    1.08
    ่
    1.06
    ص
    1.05
    Activations Density 0.000%

    No Known Activations