© 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. 123966
    Prev
    Next
    INDEX
    Explanations

    deep sea

    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
    n
    0.88
    深
    0.73
    ters
    0.70
    ra
    0.69
    ты
    0.66
    ss
    0.65
    sers
    0.63
    ль
    0.63
    溁
    0.63
    ール
    0.62
    POSITIVE LOGITS
     lezen
    0.67
     Returned
    0.67
     stunned
    0.61
    _);
    0.60
     VND
    0.59
    ")',
    0.59
     LEED
    0.58
    UND
    0.58
     維尼
    0.58
    DDD
    0.58
    Activations Density 0.002%

    No Known Activations