© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215121
    Prev
    Next
    INDEX
    Explanations

    Enron

    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_31_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
    চীন
    0.46
    ทร
    0.41
    𝒟
    0.37
     Fert
    0.37
     China
    0.36
    China
    0.36
     TFT
    0.36
     Link
    0.35
    маш
    0.35
     triumph
    0.35
    POSITIVE LOGITS
    Status
    0.41
    getStatus
    0.40
     возникает
    0.38
    FuncName
    0.38
     می‌کند
    0.36
    status
    0.35
     status
    0.35
    __()
    0.35
    statusCode
    0.34
     arises
    0.34
    Activations Density 0.000%

    No Known Activations