© 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. 49359
    Prev
    Next
    INDEX
    Explanations

    decimal points calculation

    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
    Debugger
    0.39
    érées
    0.37
    طلق
    0.37
    stered
    0.35
     članak
    0.35
    صدر
    0.35
     வெள்ளி
    0.35
    릎
    0.35
     кра
    0.34
     ieder
    0.34
    POSITIVE LOGITS
    yii
    0.38
     tricks
    0.37
    ?,?,
    0.37
     sums
    0.37
    BR
    0.35
     stunts
    0.35
    Drawable
    0.35
    Assets
    0.35
    drawable
    0.34
    माही
    0.34
    Activations Density 0.000%

    No Known Activations