© 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. 43609
    Prev
    Next
    INDEX
    Explanations

    dark elves, trace, net

    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
    ים
    0.81
    ы
    0.81
    s
    0.78
    ות
    0.71
    ز
    0.71
    ्स
    0.69
    ের
    0.69
    ات
    0.68
    siz
    0.66
    ों
    0.65
    POSITIVE LOGITS
     will
    0.73
    {'
    0.63
    )
    0.62
    a
    0.61
    ['
    0.61
    im
    0.59
    [['
    0.59
     can
    0.59
    igation
    0.56
    !
    0.55
    Activations Density 0.004%

    No Known Activations