© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174913
    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_24_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
    이
    0.61
    ي
    0.56
    der
    0.55
    ned
    0.51
    더
    0.50
    מל
    0.48
    ដៃ
    0.47
    졌
    0.47
    ერ
    0.46
    דר
    0.46
    POSITIVE LOGITS
    >?
    0.54
     defendant
    0.49
     '>
    0.47
    ｯ
    0.47
     titular
    0.46
     ≥
    0.46
     destacado
    0.46
     confronti
    0.45
     abogado
    0.45
    '।
    0.44
    Activations Density 0.000%

    No Known Activations