© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62894
    Prev
    Next
    INDEX
    Explanations

    trade winds

    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_41_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
    吗
    0.79
     ли
    0.75
    ไหม
    0.74
    嗎
    0.74
     มั้ย
    0.64
     ไหม
    0.64
    么
    0.62
    了嗎
    0.58
    了吗
    0.54
    인가
    0.52
    POSITIVE LOGITS
     trade
    1.80
     Trade
    1.75
    Trade
    1.63
    trade
    1.60
     TRADE
    1.55
    TRADE
    1.38
    贸易
    1.33
    貿易
    1.30
     trades
    1.24
     ट्रेड
    1.17
    Activations Density 0.022%

    No Known Activations