© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116739
    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.38
    <0xAF>
    0.38
    tat
    0.38
    site
    0.36
    どうぞ
    0.34
    ändigen
    0.34
     thing
    0.34
     दत्त
    0.33
    ০০০
    0.33
    regions
    0.33
    POSITIVE LOGITS
    >\<^
    0.43
    atism
    0.41
    पिक्सल
    0.41
     hydrophilic
    0.40
     Comunic
    0.40
     chromatographic
    0.40
    gdock
    0.40
     ಕಡಿಮೆ
    0.40
     customarily
    0.40
     sophistic
    0.40
    Activations Density 0.000%

    No Known Activations