© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60275
    Prev
    Next
    INDEX
    Explanations

    foreign trade and investment

    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
    wenn
    0.46
    жено
    0.39
    辏
    0.37
    𝐡
    0.36
    fromString
    0.36
    භාව
    0.35
    durch
    0.35
     மஹ
    0.34
    five
    0.34
    bine
    0.34
    POSITIVE LOGITS
    OUSE
    0.37
    AR
    0.37
     substrates
    0.37
     кукуру
    0.37
    玉米
    0.37
    ,
    0.37
    ര
    0.37
     that
    0.36
    IR
    0.35
     рисо
    0.35
    Activations Density 0.003%

    No Known Activations