© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204523
    Prev
    Next
    INDEX
    Explanations

    digits, numbers, and code formatting

    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_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
     barons
    0.20
    یت
    0.19
     NOK
    0.19
     intact
    0.18
    More
    0.18
     brethren
    0.18
    ᐃ
    0.18
     माम
    0.18
    নাথ
    0.18
    nections
    0.18
    POSITIVE LOGITS
     मसल
    0.21
    竻
    0.21
    ंजनों
    0.21
     ক্রমাগত
    0.20
     Lease
    0.20
     HEALTH
    0.20
     मांसपेश
    0.19
     कोणताही
    0.19
    ಗಳಿಗೆ
    0.19
     ಲೋ
    0.19
    Activations Density 0.012%

    No Known Activations