© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9684
    Prev
    Next
    INDEX
    Explanations

    Australia convict colony locations

    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_13_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
     Japanese
    0.61
    japanese
    0.57
    Japanese
    0.52
     япон
    0.52
     Stanley
    0.49
     ষ
    0.49
     Sakura
    0.49
     But
    0.48
    geb
    0.48
    resultSet
    0.48
    POSITIVE LOGITS
    뉴
    0.50
     न्यू
    0.49
    न्यू
    0.48
     nucl
    0.48
    নিউ
    0.47
     নিউ
    0.46
    тивный
    0.46
    右
    0.45
    航
    0.45
     erreichen
    0.45
    Activations Density 0.005%

    No Known Activations