© 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. 36527
    Prev
    Next
    INDEX
    Explanations

    gráficos de estadisticas y analisis

    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
    cosa
    0.53
    Stadium
    0.52
    igues
    0.52
    穫
    0.50
    دا
    0.49
    gage
    0.49
    gladbach
    0.48
     by
    0.48
    λεσμα
    0.48
    iggio
    0.48
    POSITIVE LOGITS
     persever
    0.63
    шат
    0.60
     发表于
    0.57
     sifatida
    0.56
    いる
    0.56
    ж
    0.56
     an
    0.55
    :",
    0.55
     レディース
    0.55
     ফার
    0.55
    Activations Density 0.001%

    No Known Activations