© 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. 37677
    Prev
    Next
    INDEX
    Explanations

    motorcycle ENGINE or CYCLE

    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
    ت
    0.92
    ä
    0.88
    لي
    0.82
    t
    0.80
    v
    0.79
    ل
    0.78
    a
    0.76
    h
    0.76
    一
    0.75
    柇
    0.73
    POSITIVE LOGITS
     danneggi
    0.80
     reclama
    0.73
     for
    0.70
     edile
    0.66
     dific
    0.65
     validar
    0.65
    ן
    0.65
     nomenclatura
    0.64
     presup
    0.64
     milioni
    0.64
    Activations Density 0.001%

    No Known Activations