© 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. 37614
    Prev
    Next
    INDEX
    Explanations

    slither ing, slumber ing

    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
    at
    1.37
    i
    1.34
    e
    1.20
    a
    1.11
    o
    1.01
    as
    0.96
    ut
    0.93
    ed
    0.92
    en
    0.90
    {
    0.89
    POSITIVE LOGITS
    ﺭ
    0.77
    لیس
    0.71
     просты
    0.70
    取り組み
    0.69
    ка
    0.68
     impuestos
    0.67
     débil
    0.67
    シンプルな
    0.66
    基本的な
    0.66
     спорттук
    0.65
    Activations Density 0.001%

    No Known Activations