© 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. 215274
    Prev
    Next
    INDEX
    Explanations

    boolean values, blank, null, none

    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
    μή
    0.42
     ჭ
    0.38
     بالإضافة
    0.38
    cPix
    0.38
    urium
    0.37
    蛎
    0.37
     crayfish
    0.36
    あら
    0.36
    朤
    0.36
    वणे
    0.36
    POSITIVE LOGITS
    bootstrap
    0.36
    oulders
    0.35
    filter
    0.34
     זאת
    0.34
    試
    0.34
    check
    0.32
     Polynomial
    0.32
     gradient
    0.32
     Bench
    0.32
     unmet
    0.32
    Activations Density 0.008%

    No Known Activations