© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31357
    Prev
    Next
    INDEX
    Explanations

    common words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    宠
    0.34
     خصوصی
    0.34
     Of
    0.34
    [!
    0.34
    ണ്ട
    0.32
    Между
    0.30
    Of
    0.30
     terribly
    0.29
    Interested
    0.29
     Более
    0.29
    POSITIVE LOGITS
    tenir
    0.37
    ეგის
    0.37
    ouncy
    0.34
    ულია
    0.33
    plin
    0.30
    cales
    0.30
    ّم
    0.30
    lico
    0.30
    čni
    0.30
    시키는
    0.30
    Activations Density 0.069%

    No Known Activations