© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236771
    Prev
    Next
    INDEX
    Explanations

    describes function or purpose

    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_32_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
    धरी
    0.31
     बोले
    0.31
    తున్నారు
    0.31
     ഉണ്ട്
    0.30
     fréquent
    0.30
    >[
    0.29
     చేస్త
    0.29
    న్నారు
    0.29
     می‌ده
    0.29
     दीप
    0.29
    POSITIVE LOGITS
     they
    0.45
    他們
    0.44
    他们
    0.44
     ისინი
    0.44
    我們
    0.43
    这
    0.41
    大家
    0.41
    这些
    0.41
     इसने
    0.41
     તેણે
    0.41
    Activations Density 0.019%

    No Known Activations