© 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. 203739
    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
     ilustraciones
    0.39
     vu
    0.38
     juc
    0.37
     $(\
    0.36
    abbo
    0.35
     $)$
    0.35
    Respondent
    0.35
    upar
    0.35
     ஒ
    0.34
     left
    0.34
    POSITIVE LOGITS
    сності
    0.39
     अमित
    0.38
     फोर्थ
    0.37
     MEX
    0.36
    AMES
    0.35
     سازی
    0.35
     plat
    0.35
    ElementSibling
    0.34
    ന്നും
    0.33
     mempengaruhi
    0.33
    Activations Density 0.000%

    No Known Activations