© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85682
    Prev
    Next
    INDEX
    Explanations

    parser.add_argument

    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
    ب
    0.78
    م
    0.75
     It
    0.70
    מ
    0.67
     않았
    0.64
    あります
    0.63
    ב
    0.63
     There
    0.62
     $
    0.62
    س
    0.61
    POSITIVE LOGITS
    ки
    0.71
    ри
    0.65
    I
    0.64
    körper
    0.64
    köz
    0.63
    OTROS
    0.61
    kosten
    0.59
    kiego
    0.59
     potrz
    0.59
    IAT
    0.59
    Activations Density 0.001%

    No Known Activations