© 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. 89346
    Prev
    Next
    INDEX
    Explanations

    plenty to choose from

    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
     Kanye
    0.62
    usian
    0.62
     또한
    0.58
     또는
    0.56
     व्याज
    0.56
    <unused497>
    0.55
     อย่า
    0.55
    裒
    0.55
    ToAction
    0.54
     serta
    0.53
    POSITIVE LOGITS
    t
    0.76
    ام
    0.72
    ನಿ
    0.64
     richting
    0.63
    لة
    0.59
    0.59
    স
    0.58
    ية
    0.57
     \
    0.56
    త
    0.54
    Activations Density 0.001%

    No Known Activations