© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50126
    Prev
    Next
    INDEX
    Explanations

    stock

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    股东
    0.49
    หุ้น
    0.41
     Share
    0.39
    鮮
    0.39
     शेयर
    0.38
    orne
    0.37
     Shareholders
    0.37
    Share
    0.37
    Outline
    0.37
    真っ
    0.36
    POSITIVE LOGITS
     движения
    0.47
    istisch
    0.42
    ເຄ
    0.41
     движение
    0.40
     enzymes
    0.40
     فعالیت
    0.39
     positional
    0.39
    <unused10>
    0.39
     actividades
    0.38
     POSITION
    0.38
    Activations Density 0.004%

    No Known Activations