© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33386
    Prev
    Next
    INDEX
    Explanations

    struct definition syntax

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    :
    0.88
    ;
    0.87
    '
    0.80
    \
    0.77
    ]
    0.76
     OF
    0.75
    >
    0.71
    ()
    0.69
     đổi
    0.68
     isomers
    0.68
    POSITIVE LOGITS
    ر
    0.80
    ీయ
    0.77
    ot
    0.76
    ur
    0.73
    that
    0.73
    un
    0.73
    ॉन
    0.71
    وتر
    0.70
    وبر
    0.69
    ע
    0.69
    Activations Density 0.009%

    No Known Activations