© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89838
    Prev
    Next
    INDEX
    Explanations

    code blocks and structures

    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_23_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
    理論
    0.43
     theorist
    0.40
     specialization
    0.39
     கோட்ப
    0.38
    oci
    0.37
     benz
    0.36
    続
    0.36
    いう
    0.35
     نظری
    0.35
     teor
    0.34
    POSITIVE LOGITS
     상세보기
    0.46
    ٗ
    0.42
    जयपुर
    0.40
     calmly
    0.40
    
    0.40
     वो
    0.39
    alama
    0.38
    jskiego
    0.38
     없습니다
    0.38
    ала
    0.38
    Activations Density 0.000%

    No Known Activations