© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127184
    Prev
    Next
    INDEX
    Explanations

    Cortex and blur

    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
    ের
    1.13
    ों
    0.93
    ы
    0.88
    نې
    0.87
    ード
    0.83
    ા
    0.81
    ς
    0.81
    ږئ
    0.80
    ی
    0.80
     නිෂ්
    0.79
    POSITIVE LOGITS
    t
    1.24
     It
    0.93
    in
    0.83
    I
    0.77
     I
    0.73
     (
    0.68
    ian
    0.65
    upp
    0.64
    aking
    0.63
    0.63
    Activations Density 0.001%

    No Known Activations