© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5580
    Prev
    Next
    INDEX
    Explanations

    financial markets and trading

    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_39_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
     grain
    0.42
    ⼈
    0.40
    getSource
    0.38
    陰
    0.37
     Grain
    0.36
    Sterling
    0.36
    sterling
    0.36
    SelectedItem
    0.36
    阴
    0.36
     poison
    0.35
    POSITIVE LOGITS
     trading
    0.77
     Trading
    0.69
    trading
    0.68
    Trading
    0.66
    market
    0.61
    價格
    0.61
     ट्रेडिंग
    0.60
     traders
    0.59
     market
    0.59
    交易
    0.59
    Activations Density 0.117%

    No Known Activations