© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2831
    Prev
    Next
    INDEX
    Explanations

    alternative options, investments, learning, perspectives, economic, terms, approaches, route

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ことになる
    1.79
     emek
    1.68
    ্ড
    1.57
    dan
    1.56
     abundantly
    1.55
    逋
    1.54
    本発明
    1.54
    teeth
    1.54
     attuned
    1.54
     pë
    1.51
    POSITIVE LOGITS
    ی
    1.78
    icted
    1.76
    詁
    1.71
    ни
    1.66
    स्थ्य
    1.62
     shrimp
    1.62
     использования
    1.54
    savvy
    1.54
    лари
    1.50
    य
    1.44
    Activations Density 0.055%

    No Known Activations