© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59975
    Prev
    Next
    INDEX
    Explanations

    template delimiters or control flow

    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
    upta
    0.62
    k
    0.58
     up
    0.56
    ae
    0.56
    šten
    0.55
    c
    0.54
    up
    0.54
    ↵
    0.54
    ua
    0.53
    aa
    0.52
    POSITIVE LOGITS
     коды
    0.62
     Wochenende
    0.60
    Totals
    0.57
     Netzwerk
    0.55
    Multicolored
    0.55
     ঠিকানা
    0.55
    Defocused
    0.55
    ‌هایی
    0.54
     ছো
    0.52
     নিউইয়
    0.52
    Activations Density 0.002%

    No Known Activations