© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37743
    Prev
    Next
    INDEX
    Explanations

    punctuation or foreign

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ließend
    0.45
     tomonidan
    0.38
    ",[],"
    0.37
    েন্দ্রনাথ
    0.36
    ishops
    0.35
    chek
    0.35
    ześnie
    0.35
     fapt
    0.34
    andfeel
    0.34
    elseif
    0.34
    POSITIVE LOGITS
     أن
    0.80
    ，
    0.78
     ان
    0.75
     إن
    0.73
     att
    0.70
    ،
    0.67
     том
    0.66
     ،
    0.57
    ﹐
    0.57
    ,
    0.55
    Activations Density 0.048%

    No Known Activations