© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36744
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, and symbols

    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_11_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
    等方面
    0.48
    ATH
    0.47
     Precious
    0.47
    ，
    0.46
    umin
    0.45
    টো
    0.45
     فض
    0.45
     Diner
    0.45
    essä
    0.45
     المرأة
    0.45
    POSITIVE LOGITS
    یک
    0.85
    น
    0.82
    न
    0.80
    ි
    0.72
    ın
    0.67
    ı
    0.67
    प
    0.65
     crippled
    0.63
    िक
    0.63
    ной
    0.62
    Activations Density 0.018%

    No Known Activations