© 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. 36386
    Prev
    Next
    INDEX
    Explanations

    `@injectable`, `@outlook.com`, `@spec`, `@doc`, `dataclass`

    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
    ra
    0.74
    raa
    0.68
    ي
    0.63
     يعمل
    0.62
     فريبي
    0.62
     weathered
    0.61
    ri
    0.60
    ري
    0.59
     Цуки
    0.59
     дел
    0.59
    POSITIVE LOGITS
     for
    0.84
    0
    0.75
    .
    0.73
    ка
    0.72
    0.67
    ز
    0.65
    uit
    0.63
    此
    0.63
    อะไร
    0.62
    าน
    0.60
    Activations Density 0.001%

    No Known Activations