© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59406
    Prev
    Next
    INDEX
    Explanations

    总而言之

    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
    er
    0.84
    os
    0.83
    in
    0.82
    i
    0.81
    un
    0.80
    o
    0.78
    Name
    0.75
    u
    0.75
    us
    0.73
    on
    0.73
    POSITIVE LOGITS
    מי
    0.77
    ње
    0.68
    ש
    0.66
     Buckeyes
    0.64
    酰
    0.62
    ամ
    0.61
    炎症
    0.60
     adolesc
    0.60
     শত্র
    0.59
    ган
    0.59
    Activations Density 0.000%

    No Known Activations