© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146576
    Prev
    Next
    INDEX
    Explanations

    '

    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_59_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
    s
    0.47
    man
    0.42
    sin
    0.42
    TABLE
    0.42
    that
    0.41
    Sin
    0.41
    Table
    0.40
    table
    0.40
    TOD
    0.39
    son
    0.39
    POSITIVE LOGITS
     s
    0.56
     س
    0.54
     স
    0.49
     الس
    0.45
     स
    0.43
     nt
    0.43
    ‘‘
    0.43
    楍
    0.43
     його
    0.42
    ‌,
    0.42
    Activations Density 0.009%

    No Known Activations