© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90387
    Prev
    Next
    INDEX
    Explanations

    stock market 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_11_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
     (
    0.59
    at
    0.55
     /
    0.55
     –
    0.55
    ov
    0.54
     Les
    0.54
    le
    0.52
    Migration
    0.52
     teatro
    0.52
     Pur
    0.52
    POSITIVE LOGITS
    삵
    0.60
    ک
    0.54
     کارڈ
    0.54
    약
    0.54
    クセル
    0.53
    まさ
    0.52
     стиля
    0.52
    ಠ
    0.51
    ゆる
    0.50
     ವಿಧಾನಸ
    0.50
    Activations Density 0.070%

    No Known Activations