© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17615
    Prev
    Next
    INDEX
    Explanations

    HTTP/HTTPS protocol

    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
    LI
    0.29
    asth
    0.29
     Leukemia
    0.28
    '.
    0.28
    <unused60>
    0.28
    as
    0.28
    left
    0.27
    P
    0.27
    ',
    0.27
    ee
    0.26
    POSITIVE LOGITS
     ríos
    0.33
     acids
    0.30
     évident
    0.29
     innovating
    0.28
     rivers
    0.28
     ちゃ
    0.28
    χύ
    0.27
     Dion
    0.27
     nước
    0.27
     नदियों
    0.26
    Activations Density 0.011%

    No Known Activations