© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 92129
    Prev
    Next
    INDEX
    Explanations

    parentheses and list items

    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
    ed
    0.57
    ت
    0.55
     fizeram
    0.49
    as
    0.49
    et
    0.48
    "));
    0.48
    uhe
    0.48
     позволяют
    0.47
    it
    0.46
    a
    0.46
    POSITIVE LOGITS
    (
    0.54
    Residential
    0.48
    és
    0.47
    )।
    0.45
    PropertySheets
    0.44
     Mä
    0.43
     Residential
    0.42
    ).
    0.42
    {
    0.42
     Sä
    0.40
    Activations Density 0.010%

    No Known Activations