© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36107
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
     that
    1.05
    2
    0.98
    ב
    0.83
    場合は
    0.80
    ை
    0.80
    サイズ
    0.79
    <0x0D>
    0.79
    ೆ
    0.79
     था
    0.77
    २
    0.77
    POSITIVE LOGITS
    are
    1.00
    ACO
    0.88
    l
    0.86
    ESE
    0.80
    OrderFlight
    0.80
     செய்யும்
    0.80
    arm
    0.79
    MCA
    0.79
    يني
    0.78
     radionuclide
    0.77
    Activations Density 0.000%

    No Known Activations