© 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. 56641
    Prev
    Next
    INDEX
    Explanations

    youcandoit

    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
    ン
    0.66
     său
    0.60
    giène
    0.57
     próprios
    0.57
    á
    0.57
     negócios
    0.56
    ፆ
    0.55
     negócio
    0.55
     enzyme
    0.55
     صہیون
    0.55
    POSITIVE LOGITS
    at
    0.98
    had
    0.70
    k
    0.58
     Oro
    0.57
     Cover
    0.56
    or
    0.55
     couldn
    0.54
     Corm
    0.54
     إضافة
    0.54
    chtigt
    0.54
    Activations Density 0.003%

    No Known Activations