© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53046
    Prev
    Next
    INDEX
    Explanations

    date October

    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_31_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
    iedy
    0.37
    잌
    0.33
    ideo
    0.31
    🌽
    0.31
    们
    0.30
     exercising
    0.30
    다는
    0.30
    ：
    0.29
     cornice
    0.29
     Corn
    0.29
    POSITIVE LOGITS
     pronounced
    0.33
     onDestroy
    0.29
     innehåller
    0.29
     spalle
    0.29
    ×</
    0.29
    Destroy
    0.28
    almost
    0.28
    onDestroy
    0.28
     збіль
    0.28
    对照
    0.28
    Activations Density 0.002%

    No Known Activations