© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 963
    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_39_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
    ügel
    0.38
    īd
    0.37
    ᚄ
    0.35
     مسلمانوں
    0.35
     তুর
    0.34
    "%>
    0.34
    骓
    0.34
    塞尔
    0.34
    linkCell
    0.33
     التمث
    0.33
    POSITIVE LOGITS
    constant
    0.43
     constant
    0.38
     ਬਾ
    0.36
    boxing
    0.36
    自然
    0.34
    brides
    0.34
     здравоохранения
    0.33
     boxing
    0.33
    bent
    0.32
     amore
    0.32
    Activations Density 0.000%

    No Known Activations