© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29962
    Prev
    Next
    INDEX
    Explanations

    Wayland, xrandr, xprop

    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
     X
    0.57
    X
    0.48
     Х
    0.44
     एक्सरे
    0.43
     x
    0.43
     Χ
    0.41
     display
    0.40
     Kontrolle
    0.39
     Display
    0.39
    display
    0.38
    POSITIVE LOGITS
     pö
    0.40
    ㄟ
    0.40
     категорії
    0.38
    Desktop
    0.37
    鄯
    0.37
    榴
    0.36
    Harm
    0.36
    ++,
    0.36
     Bulgaria
    0.35
     conqu
    0.35
    Activations Density 0.010%

    No Known Activations