© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124668
    Prev
    Next
    INDEX
    Explanations

    K-Fold cross-validation

    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_3_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
    i
    1.28
    t
    1.13
    it
    1.09
    in
    1.02
    a
    0.98
     it
    0.95
    w
    0.93
    ה
    0.88
    ar
    0.88
    ي
    0.87
    POSITIVE LOGITS
    к
    1.04
    ية
    0.93
    ক
    0.92
    0.73
    IS
    0.70
    گ
    0.70
    OP
    0.70
    у
    0.70
     вій
    0.68
    ER
    0.68
    Activations Density 0.000%

    No Known Activations