© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165276
    Prev
    Next
    INDEX
    Explanations

    Hawaii, Diamond Head, loco moco

    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_13_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
    का
    0.55
    ereur
    0.54
    ਫ
    0.53
    ι
    0.52
    ما
    0.52
    ह
    0.52
    沖縄
    0.51
    इन
    0.50
     Airport
    0.50
     Jérôme
    0.50
    POSITIVE LOGITS
     kru
    0.50
     продъл
    0.50
     продолжаем
    0.49
     acht
    0.48
     mange
    0.48
     pastry
    0.48
     quilting
    0.47
     multis
    0.46
     myel
    0.46
     cią
    0.46
    Activations Density 0.003%

    No Known Activations