© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10279
    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_40_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
     qualified
    0.51
     CFA
    0.50
     Qualified
    0.49
     CFP
    0.48
    CCl
    0.46
     qualifies
    0.45
    Qualified
    0.45
     квали
    0.44
    qualified
    0.43
     身
    0.43
    POSITIVE LOGITS
     सर्ट
    0.44
    Rail
    0.43
    Certification
    0.43
     certification
    0.41
     сертифика
    0.40
     woh
    0.40
    iagn
    0.40
     चौथ
    0.40
     vouch
    0.38
     Certification
    0.38
    Activations Density 0.008%

    No Known Activations