© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45452
    Prev
    Next
    INDEX
    Explanations

    phenomenal

    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
    frequencies
    0.73
    Не
    0.73
    К
    0.72
    convén
    0.71
    П
    0.70
    leaflet
    0.68
    listItem
    0.68
    bedrooms
    0.67
    ПК
    0.67
    ꫝ
    0.67
    POSITIVE LOGITS
    <0x0D>
    0.81
     been
    0.79
     beer
    0.78
     who
    0.74
     sehr
    0.73
     muere
    0.73
     zwią
    0.72
     zeit
    0.72
    ed
    0.71
     has
    0.71
    Activations Density 0.001%

    No Known Activations