© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170432
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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_56_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
    freie
    0.40
     --------");
    0.39
    苙
    0.39
    )});
    0.38
    measured
    0.37
    衩
    0.36
    getFullYear
    0.35
    нный
    0.35
    பாவ
    0.35
    gutter
    0.35
    POSITIVE LOGITS
     ‘
    0.54
    ‘
    0.47
     (‘
    0.44
     ‚
    0.43
     `
    0.43
     kd
    0.39
    `.
    0.38
    ｢
    0.38
    ¹.
    0.37
    ‚
    0.37
    Activations Density 0.003%

    No Known Activations