© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96282
    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_14_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
     молока
    0.50
    '*
    0.50
    জ
    0.48
    '
    0.48
    প্রধানমন্ত্রী
    0.48
     допомо
    0.47
    جام
    0.47
    addEnemy
    0.47
     стату
    0.46
     تجاوز
    0.45
    POSITIVE LOGITS
    uration
    0.55
    ural
    0.53
    s
    0.51
    sph
    0.49
    off
    0.49
    erna
    0.49
    aire
    0.47
    ler
    0.47
    like
    0.47
     Off
    0.47
    Activations Density 0.000%

    No Known Activations