© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5651
    Prev
    Next
    INDEX
    Explanations

    website pages and links

    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_3_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
    ه
    0.87
    要在
    0.75
    jų
    0.72
    o
    0.69
    ി
    0.68
     fallait
    0.68
    बता
    0.64
    ה
    0.63
    ್ಟ
    0.63
    ம்
    0.63
    POSITIVE LOGITS
    fontsize
    0.64
     Appendix
    0.58
     Burgundy
    0.58
    Velocity
    0.57
     وعلى
    0.57
    絡
    0.56
     acaso
    0.56
     Mlad
    0.55
    partisan
    0.55
     Cruises
    0.55
    Activations Density 0.567%

    No Known Activations