© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90704
    Prev
    Next
    INDEX
    Explanations

    campus-wide network

    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_3_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
    '
    0.87
    [
    0.65
    APE
    0.63
     为
    0.61
         
    0.60
     cubed
    0.60
    ceived
    0.59
     yakın
    0.59
     ancien
    0.58
     Opportunities
    0.57
    POSITIVE LOGITS
    да
    0.62
    casino
    0.62
    inę
    0.59
    id
    0.58
    eris
    0.58
    ším
    0.58
    는
    0.58
    ásticos
    0.57
    قة
    0.57
    الية
    0.56
    Activations Density 0.001%

    No Known Activations