© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197971
    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_12_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
    ?“
    0.60
    .“
    0.58
     बाजार
    0.55
    V
    0.54
    烈的
    0.51
    нього
    0.50
    intestin
    0.50
    inum
    0.50
    idades
    0.49
     màu
    0.49
    POSITIVE LOGITS
     อาจ
    0.70
    אם
    0.64
    אן
    0.58
     alleges
    0.58
    ’
    0.56
     risks
    0.55
     jis
    0.55
     হে
    0.53
     M
    0.52
     ss
    0.52
    Activations Density 0.000%

    No Known Activations