© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23967
    Prev
    Next
    INDEX
    Explanations

    UI components and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    <div>
    0.40
    ÿ
    0.39
    ǿ
    0.36
    abilă
    0.36
     seepage
    0.35
     (?)
    0.33
     dispense
    0.33
     общения
    0.33
    管理局
    0.33
     Inserting
    0.33
    POSITIVE LOGITS
     variant
    0.48
     variation
    0.40
    ReactNative
    0.39
     javascript
    0.39
    ython
    0.39
     Variant
    0.38
     နဲ့
    0.37
    :'.
    0.37
     variations
    0.36
     maiden
    0.36
    Activations Density 0.003%

    No Known Activations