© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193471
    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
    Negative Logits
     ποι
    0.43
    CMI
    0.42
     sambil
    0.42
    স্থলে
    0.41
    𝐭
    0.39
    сэн
    0.38
    ជាមួយ
    0.38
    अधिकांश
    0.38
    ↵
    0.38
     باقی
    0.37
    POSITIVE LOGITS
     prank
    0.46
     pull
    0.41
     crashed
    0.40
     nine
    0.39
     finalised
    0.39
     incompre
    0.38
     lifted
    0.38
     horrifying
    0.38
     condem
    0.38
     geometric
    0.38
    Activations Density 0.000%

    No Known Activations