© 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. 254156
    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
    തെ
    0.41
     қо
    0.38
     soak
    0.38
    forName
    0.36
    "));
    0.36
    }}}}$
    0.36
    inception
    0.35
    哉
    0.35
    Ƅ
    0.35
     nový
    0.35
    POSITIVE LOGITS
    änger
    0.36
    委員會
    0.35
    تبقى
    0.34
    ဍ
    0.33
    minipage
    0.33
     aparte
    0.33
    Volatility
    0.33
    Berry
    0.33
     volunteered
    0.32
    claw
    0.32
    Activations Density 0.000%

    No Known Activations