© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11014
    Prev
    Next
    INDEX
    Explanations

    Learning for Justice

    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
    ation
    0.51
    ي
    0.50
    so
    0.50
    i
    0.49
    io
    0.48
    ta
    0.47
    ibatkan
    0.47
    ased
    0.46
    will
    0.46
    iyat
    0.45
    POSITIVE LOGITS
    CLS
    0.48
     గ్రామ
    0.48
    CMP
    0.48
    䳕
    0.46
    Ὅ
    0.45
    Bootstrap
    0.44
    Black
    0.44
    県
    0.43
    ELS
    0.43
    介绍了
    0.43
    Activations Density 0.013%

    No Known Activations