© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192579
    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_4_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
    t
    0.67
    mä
    0.59
    tä
    0.57
    <0x80>
    0.56
    tive
    0.56
    kom
    0.55
    定律
    0.55
    né
    0.54
    lage
    0.54
     škol
    0.54
    POSITIVE LOGITS
    دی
    0.63
    ’
    0.63
    بی
    0.58
    ר
    0.56
    سی
    0.54
    ری
    0.54
    یاء
    0.54
    કિંગ
    0.51
    민
    0.50
    ות
    0.50
    Activations Density 0.000%

    No Known Activations