© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140038
    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_37_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
     व्हाउचर
    0.48
    瞍
    0.44
    车
    0.43
     때
    0.43
    NeedConnect
    0.41
     extension
    0.41
    付ける
    0.40
     넣
    0.39
     〢
    0.39
    车的
    0.39
    POSITIVE LOGITS
    ils
    0.38
    سوم
    0.36
     secure
    0.36
     दगडा
    0.35
     Fibonacci
    0.35
    byshire
    0.34
    secure
    0.34
    ంశ
    0.34
    mell
    0.34
    ocks
    0.33
    Activations Density 0.000%

    No Known Activations