© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9743
    Prev
    Next
    INDEX
    Explanations

    main code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     JDK
    0.80
     메서
    0.79
    OpenJDK
    0.77
    𝘶
    0.76
    ）.
    0.75
    ྭ
    0.74
    🩹
    0.74
    䖝
    0.73
    LLDB
    0.72
    󰡕
    0.72
    POSITIVE LOGITS
     Main
    0.95
     main
    0.91
    Main
    0.90
    main
    0.83
     driver
    0.69
     ma
    0.69
     उत्तम
    0.68
     मुख्य
    0.67
     મુખ્ય
    0.67
     مدر
    0.67
    Activations Density 0.024%

    No Known Activations