© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1960
    Prev
    Next
    INDEX
    Explanations

    use (

    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_40_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
    扫
    0.40
    chyné
    0.39
     化粧
    0.39
    مین
    0.38
    ))}{
    0.37
     carbohydrate
    0.37
     carbohydrates
    0.37
    ួរ
    0.35
    )}+\
    0.35
     av
    0.35
    POSITIVE LOGITS
     expres
    0.57
     expresión
    0.54
     expressão
    0.54
     express
    0.52
     экс
    0.52
     এক্সপ্রেস
    0.50
     екс
    0.50
     expr
    0.49
    表达
    0.46
    表达式
    0.45
    Activations Density 0.003%

    No Known Activations