© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 26843
    Prev
    Next
    INDEX
    Explanations

    forms and form handling

    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_10_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
    ی
    0.72
    AT
    0.71
    t
    0.68
    ES
    0.67
    y
    0.66
    OD
    0.66
    چین
    0.64
    یی
    0.63
    nın
    0.62
    s
    0.62
    POSITIVE LOGITS
    Form
    0.77
     شكل
    0.71
     puso
    0.70
     फॉर्म
    0.70
     форм
    0.68
    ationen
    0.67
    apping
    0.64
    Selectors
    0.63
    age
    0.63
    Forms
    0.63
    Activations Density 0.003%

    No Known Activations