© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4671
    Prev
    Next
    INDEX
    Explanations

    output file formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     FIXME
    0.82
    然後
    0.75
    $\--
    0.71
     foy
    0.70
    ال
    0.70
    tick
    0.70
     trimester
    0.69
    αν
    0.68
    員
    0.68
    JlcG
    0.68
    POSITIVE LOGITS
    見る
    0.73
    みる
    0.68
     всего
    0.65
    هَا
    0.62
     руководитель
    0.62
     gauging
    0.61
     cbind
    0.61
     লোককে
    0.61
     chromospheres
    0.60
    𝓮
    0.59
    Activations Density 0.000%

    No Known Activations