© 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. 5710
    Prev
    Next
    INDEX
    Explanations

    #include file statements

    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
    ️
    0.93
    measures
    0.75
    updated
    0.72
    NESS
    0.72
    t
    0.71
     آمده
    0.69
    quarters
    0.69
    exceptions
    0.69
    йся
    0.67
     pierced
    0.67
    POSITIVE LOGITS
    ব
    0.86
    ти
    0.85
     goû
    0.73
     Toutes
    0.72
    ̀ng
    0.72
     provoqu
    0.71
    스코
    0.67
     stake
    0.67
    ches
    0.66
    дие
    0.66
    Activations Density 0.006%

    No Known Activations