© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13915
    Prev
    Next
    INDEX
    Explanations

    code block start

    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_15_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
     будів
    0.30
     stave
    0.29
     erecting
    0.29
     ERISA
    0.29
     specifiche
    0.29
    鎿
    0.28
     yù
    0.28
     prepares
    0.28
     polishing
    0.28
     Wolfram
    0.28
    POSITIVE LOGITS
    r
    0.37
    b
    0.36
    k
    0.33
    F
    0.33
    flow
    0.32
    in
    0.31
    ル
    0.31
    a
    0.31
    waste
    0.30
    $
    0.30
    Activations Density 0.049%

    No Known Activations