© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205453
    Prev
    Next
    INDEX
    Explanations

    match or off

    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_6_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
    ’
    1.26
    ר
    1.08
    N
    0.99
    It
    0.97
    '
    0.94
    ON
    0.91
    ।
    0.90
    Ş
    0.89
    স
    0.88
    on
    0.88
    POSITIVE LOGITS
    ia
    0.87
     jeopard
    0.87
    y
    0.87
    áce
    0.82
     for
    0.81
    iden
    0.78
     بواسطة
    0.76
    est
    0.76
     vontade
    0.75
    ný
    0.75
    Activations Density 0.000%

    No Known Activations