© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136922
    Prev
    Next
    INDEX
    Explanations

    works for

    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_37_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
     chi
    0.41
     off
    0.36
     arbit
    0.36
     Ach
    0.35
     brokers
    0.35
     ট্রেক
    0.35
     Cio
    0.35
    ី
    0.34
     Lov
    0.34
     치
    0.34
    POSITIVE LOGITS
     работают
    0.40
     বিপক্ষে
    0.40
    orylation
    0.38
    working
    0.38
     Denton
    0.38
    働
    0.37
    有用
    0.36
    تش
    0.36
    适用
    0.36
     perfettamente
    0.36
    Activations Density 0.003%

    No Known Activations