© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27615
    Prev
    Next
    INDEX
    Explanations

    Schaub / Schafer / Schau

    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_10_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
    y
    0.84
    د
    0.82
    ز
    0.73
    st
    0.70
    ج
    0.70
    blog
    0.69
    zhang
    0.68
    م
    0.67
    >
    0.66
    ktion
    0.65
    POSITIVE LOGITS
    も
    1.01
    که
    0.81
    ak
    0.80
    ين
    0.77
    ăț
    0.76
     in
    0.75
    の一
    0.75
    もら
    0.75
    がい
    0.73
     μιας
    0.71
    Activations Density 0.001%

    No Known Activations