© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15398
    Prev
    Next
    INDEX
    Explanations

    International economic trade and theory

    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_40_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
    αιν
    0.39
    ãy
    0.37
    ERRORTYPE
    0.36
    市场的
    0.36
    äub
    0.36
    猜
    0.36
     whisk
    0.35
    坐
    0.35
     cognit
    0.35
     kraft
    0.35
    POSITIVE LOGITS
     Ricardo
    0.50
     गाव
    0.50
     International
    0.46
     Ric
    0.46
    INTERNATIONAL
    0.45
    Ric
    0.45
     الدولية
    0.45
     الدولي
    0.44
     international
    0.44
     अंतरराष्ट्रीय
    0.43
    Activations Density 0.033%

    No Known Activations