© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125688
    Prev
    Next
    INDEX
    Explanations

    holy grail, symbol, month, basil

    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
    ﺭ
    0.86
    l
    0.83
    ﺍ
    0.73
     insulating
    0.71
     (
    0.69
    all
    0.66
    IDAY
    0.66
    are
    0.65
    ian
    0.64
    io
    0.64
    POSITIVE LOGITS
    في
    0.77
    。</
    0.75
    ).</
    0.75
    يق
    0.71
    كو
    0.71
    تر
    0.69
    تك
    0.69
    去
    0.69
    سك
    0.68
    লিখিত
    0.68
    Activations Density 0.001%

    No Known Activations