© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172322
    Prev
    Next
    INDEX
    Explanations

    highly likely

    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_20_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
     खतरा
    0.36
     COLLATE
    0.35
     রিটার
    0.35
     Mitgl
    0.34
    逞
    0.34
    rootScope
    0.33
    唷
    0.33
     rằng
    0.32
    しており
    0.32
     ખ્ર
    0.32
    POSITIVE LOGITS
    ぼ
    0.36
     pret
    0.34
     steel
    0.33
     satellite
    0.33
     lightest
    0.33
     Alas
    0.33
    steel
    0.32
    जैसा
    0.32
     IB
    0.32
     année
    0.32
    Activations Density 0.003%

    No Known Activations