© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209107
    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_56_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
     خدم
    0.43
    ርስዎ
    0.41
    بت
    0.38
     enlist
    0.38
    蓆
    0.37
    ptions
    0.37
    ಹಾ
    0.37
    हत
    0.36
    ගත්
    0.36
    бно
    0.36
    POSITIVE LOGITS
    ovac
    0.36
    াণী
    0.35
     like
    0.35
    Aud
    0.35
    δέ
    0.34
    Rourke
    0.33
     ø
    0.33
    isor
    0.33
     Zab
    0.33
    Dis
    0.33
    Activations Density 0.000%

    No Known Activations