© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36746
    Prev
    Next
    INDEX
    Explanations

    NBA game and statistics

    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
    𝑡
    0.62
    *$
    0.58
    伒
    0.51
     Сьогодні
    0.48
    "]);
    0.48
     کلاس
    0.48
     рус
    0.47
    人了
    0.47
    class
    0.47
    rekken
    0.46
    POSITIVE LOGITS
     agreement
    0.54
     EU
    0.50
    리기
    0.50
    s
    0.50
    aide
    0.50
     Antibodies
    0.49
    QAry
    0.49
     sedative
    0.48
     durante
    0.47
     Insurance
    0.47
    Activations Density 0.005%

    No Known Activations