© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57556
    Prev
    Next
    INDEX
    Explanations

    object file linking

    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_11_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
     a
    0.55
    as
    0.54
    1
    0.54
    প
    0.54
    Tech
    0.52
    te
    0.52
    TO
    0.52
    Br
    0.52
    Net
    0.51
    ar
    0.51
    POSITIVE LOGITS
    簡単に
    0.52
    <unused2213>
    0.46
     oatmeal
    0.46
     সংবাদপত্র
    0.46
     conceivably
    0.46
     réfrig
    0.45
     músicos
    0.44
     fáciles
    0.44
     dễ
    0.44
     osteoarthritis
    0.44
    Activations Density 0.019%

    No Known Activations