© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259611
    Prev
    Next
    INDEX
    Explanations

    magnum opus, develop, competitiveness

    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_10_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
     සම්
    0.35
    図書館
    0.33
    榴
    0.32
     внед
    0.32
     achie
    0.31
     செய்ய
    0.30
     bañ
    0.30
     최종
    0.30
    слен
    0.30
     посвя
    0.30
    POSITIVE LOGITS
     Pl
    0.36
     दवाई
    0.34
     faulty
    0.31
     Detected
    0.31
    qar
    0.31
    Pl
    0.30
     Similar
    0.30
     B
    0.30
     Far
    0.29
    ร์
    0.29
    Activations Density 0.001%

    No Known Activations