© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    maximum sum, career stats, highest/lowest

    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
    𝓮
    0.57
    alysis
    0.54
    𝓶
    0.54
     путем
    0.52
    ట్
    0.51
     ისინი
    0.51
    𝙋
    0.50
     زیرا
    0.49
     क्यो
    0.49
    लोक
    0.49
    POSITIVE LOGITS
     Lear
    0.49
    )!
    0.49
    igia
    0.48
    s
    0.47
     Bakers
    0.47
     Ferris
    0.46
    ug
    0.46
    agna
    0.45
    스템
    0.44
    ナンバー
    0.44
    Activations Density 0.020%

    No Known Activations