© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 199043
    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_4_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
    ﻳ
    0.53
     treb
    0.52
     pertenc
    0.50
     conceivably
    0.49
     busc
    0.49
    يار
    0.49
     potencialmente
    0.48
    잠
    0.48
     journée
    0.48
    ម្ម
    0.47
    POSITIVE LOGITS
     Percent
    0.48
    umbai
    0.45
     teaspoons
    0.44
    樟
    0.44
     Repeating
    0.43
     जागा
    0.43
     skaters
    0.42
    Repeating
    0.42
    周年
    0.42
     errorCode
    0.42
    Activations Density 0.000%

    No Known Activations