© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51854
    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_10_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
    gaben
    0.49
    t
    0.45
    ృతి
    0.45
     ব্যাগ
    0.44
    casa
    0.43
    ená
    0.43
    មា
    0.43
    Anth
    0.42
    によっては
    0.42
     zusätzlich
    0.41
    POSITIVE LOGITS
    의
    0.49
     जीवों
    0.46
     ASX
    0.46
     Neural
    0.46
     EUR
    0.45
     aes
    0.45
     AED
    0.44
    ffineTransform
    0.44
    췄
    0.44
    을
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.