© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168763
    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_34_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
     canceling
    0.40
     observance
    0.40
     commerciale
    0.40
     canceled
    0.39
     mại
    0.38
     intake
    0.37
     metallic
    0.37
     Inclusive
    0.37
     куп
    0.37
    챙
    0.37
    POSITIVE LOGITS
    redis
    0.41
    fifths
    0.40
    win
    0.38
    selectbox
    0.38
    oti
    0.36
    Scr
    0.36
    elabor
    0.36
    apad
    0.36
    eden
    0.35
    ice
    0.35
    Activations Density 0.000%

    No Known Activations