© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197913
    Prev
    Next
    INDEX
    Explanations

    bash commands

    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_27_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
    ക്ഷേ
    0.31
    企画
    0.31
    Ratings
    0.30
    annel
    0.29
     ٻ
    0.29
    °.
    0.29
    ബന്ധ
    0.29
     Lassen
    0.29
    Rating
    0.28
     backlash
    0.28
    POSITIVE LOGITS
    cbd
    0.35
    za
    0.34
     često
    0.33
     السنوات
    0.32
     tissu
    0.32
    ുമെന്ന്
    0.32
     الإسلام
    0.32
     छत्र
    0.32
    thorace
    0.32
    葢
    0.32
    Activations Density 0.012%

    No Known Activations