© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39944
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     раствор
    0.33
    robin
    0.31
    Arts
    0.30
    klik
    0.30
     उत्साह
    0.30
    \"{
    0.30
    Ven
    0.29
     துன்ப
    0.29
    installment
    0.29
    Click
    0.29
    POSITIVE LOGITS
     
    0.33
    ..");
    0.33
    ष्‍
    0.31
     sporad
    0.31
    ֖
    0.30
    ه‌ها
    0.30
     comun
    0.30
    ‌.
    0.30
    -}
    0.29
    ⽇
    0.29
    Activations Density 0.126%

    No Known Activations