© 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. 89516
    Prev
    Next
    INDEX
    Explanations

    president of India

    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
     pourrait
    0.63
     tuner
    0.60
     in
    0.59
     ripping
    0.57
    หลาย
    0.57
     he
    0.57
     potrebbe
    0.57
     m
    0.55
     beaucoup
    0.55
    いい
    0.55
    POSITIVE LOGITS
    ið
    0.70
    Haryana
    0.63
    Range
    0.63
    Quantidade
    0.59
    ﺸ
    0.57
    茆
    0.57
    েশ
    0.56
    Pham
    0.56
    Peru
    0.56
    CMake
    0.55
    Activations Density 0.007%

    No Known Activations