© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139123
    Prev
    Next
    INDEX
    Explanations

    gluten development

    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_12_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
     fibrils
    0.59
    𝙋
    0.57
    ಧಾರ
    0.57
     मिळाली
    0.57
     मिळाला
    0.55
     pria
    0.54
     methacrylate
    0.54
     laug
    0.54
     मांझी
    0.54
    ウィン
    0.54
    POSITIVE LOGITS
    ’
    0.68
    તાઓ
    0.47
    inson
    0.47
    ,
    0.47
    ‘
    0.47
    통
    0.46
     (
    0.44
    ^{*}$,
    0.43
    Choose
    0.43
    Default
    0.43
    Activations Density 0.001%

    No Known Activations