© 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. 88475
    Prev
    Next
    INDEX
    Explanations

    reinvent

    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
    ك
    0.79
    D
    0.74
    Ad
    0.72
    ER
    0.71
    CC
    0.70
    Res
    0.68
    Event
    0.67
    G
    0.67
    ."
    0.66
    EY
    0.66
    POSITIVE LOGITS
    '
    0.67
     geolocation
    0.61
     deputies
    0.59
     страниц
    0.59
     продуктов
    0.59
     juries
    0.57
    滸
    0.57
    >≤</
    0.56
     recharged
    0.56
    ución
    0.55
    Activations Density 0.000%

    No Known Activations