© 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. 36357
    Prev
    Next
    INDEX
    Explanations

    event loop sourcing

    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
    ية
    0.91
    ing
    0.77
    er
    0.76
    al
    0.73
    is
    0.72
    ل
    0.72
    ע
    0.69
    to
    0.68
     to
    0.67
    ur
    0.67
    POSITIVE LOGITS
     что
    0.67
     الذين
    0.61
     национа
    0.61
     църква
    0.59
     ошибка
    0.58
     ότι
    0.57
     ассоциа
    0.57
     아버지
    0.57
     accueil
    0.57
     धोने
    0.57
    Activations Density 0.002%

    No Known Activations