© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225748
    Prev
    Next
    INDEX
    Explanations

    checking for

    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_10_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
    ד
    0.30
    न
    0.30
    ്ര
    0.29
    нном
    0.29
    for
    0.28
     Продол
    0.27
    ER
    0.27
     aaya
    0.27
    ST
    0.27
     Совета
    0.27
    POSITIVE LOGITS
    ing
    0.30
     is
    0.28
    arbeiter
    0.28
    a
    0.26
    /
    0.25
    isch
    0.25
    ids
    0.25
     cascade
    0.25
    arang
    0.24
    istico
    0.24
    Activations Density 0.019%

    No Known Activations