© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27156
    Prev
    Next
    INDEX
    Explanations

    exchange, trade, swap

    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_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
    is
    1.38
    ле
    0.94
    ي
    0.86
    ро
    0.85
    ně
    0.85
    ان
    0.84
    к
    0.84
    n
    0.82
    ن
    0.82
    ge
    0.82
    POSITIVE LOGITS
     exchanging
    0.89
     EXCHANGE
    0.83
     обмен
    0.81
     Exchange
    0.79
     exchanges
    0.74
     Swap
    0.74
    শন
    0.72
     of
    0.71
    
    0.71
     exchange
    0.71
    Activations Density 0.035%

    No Known Activations