© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242496
    Prev
    Next
    INDEX
    Explanations

    trade agreements

    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
     mot
    0.42
    IMATE
    0.39
    Matcher
    0.37
     marcar
    0.37
    闯
    0.36
    闖
    0.36
    marked
    0.35
    run
    0.35
     trade
    0.35
     run
    0.34
    POSITIVE LOGITS
    峯
    0.45
     മനസ
    0.41
    wellness
    0.39
    পশ্চ
    0.38
    ピーク
    0.37
     അര
    0.37
    ố
    0.36
    TempVal
    0.36
    labs
    0.35
    ొప్ప
    0.35
    Activations Density 0.001%

    No Known Activations