© 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. 171049
    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
    high
    0.40
    HIGH
    0.39
     HIGH
    0.36
    High
    0.35
     HIG
    0.35
    HIG
    0.34
    çi
    0.34
    ﻳ
    0.33
     high
    0.33
     rokov
    0.32
    POSITIVE LOGITS
     amores
    0.38
     দেওয়া
    0.37
     осо
    0.36
    ིས་
    0.36
     экран
    0.36
    けます
    0.36
     écran
    0.35
    掷
    0.34
     অতএব
    0.34
    escape
    0.33
    Activations Density 0.000%

    No Known Activations