© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48481
    Prev
    Next
    INDEX
    Explanations

    window, Hierarchy, Explorer

    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_31_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
    ោម
    0.39
    zył
    0.36
    ॐ
    0.34
    peror
    0.34
     aumentó
    0.34
    λία
    0.33
     IDE
    0.33
     souci
    0.33
    Ⅵ
    0.33
     apostila
    0.33
    POSITIVE LOGITS
     राजप
    0.41
     पर्यवे
    0.37
     Snack
    0.37
     Shopping
    0.37
     collapsed
    0.37
     ContentView
    0.37
    erview
    0.37
     Lista
    0.36
     सुविधाजनक
    0.36
    TreeView
    0.36
    Activations Density 0.001%

    No Known Activations