© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13855
    Prev
    Next
    INDEX
    Explanations

    Bayes' Theorem, chi-squared, trapezoidal

    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_40_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
     Differential
    0.49
    Differential
    0.45
     differential
    0.44
    differential
    0.39
     Dame
    0.36
     differentially
    0.36
    inkan
    0.35
    渐
    0.35
    Dame
    0.35
    伍
    0.35
    POSITIVE LOGITS
     Bon
    0.70
    Bon
    0.66
     bon
    0.64
    bon
    0.55
     Parse
    0.53
     Бон
    0.52
     Bonnet
    0.46
    ボン
    0.46
     Jensen
    0.45
    Jensen
    0.44
    Activations Density 0.106%

    No Known Activations