© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11361
    Prev
    Next
    INDEX
    Explanations

    GUI windows and dialogs

    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_40_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
    页
    0.41
     باند
    0.40
     webpages
    0.40
     Tubes
    0.37
     pages
    0.37
     brewer
    0.37
     пло
    0.36
     प्लेयर्स
    0.36
    浃
    0.36
     plant
    0.36
    POSITIVE LOGITS
     window
    1.39
     Window
    1.31
    window
    1.30
    Window
    1.27
    窗口
    1.26
    ウィンドウ
    1.13
     windows
    1.07
     fenêtre
    1.05
     WINDOW
    1.05
     ventana
    1.04
    Activations Density 0.196%

    No Known Activations