© 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. 206697
    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
     അവത
    0.45
    ैट
    0.41
    eded
    0.39
     merged
    0.38
     ойно
    0.38
    വിട
    0.38
     Racial
    0.38
    iflor
    0.38
     ሴ
    0.37
    True
    0.36
    POSITIVE LOGITS
    झा
    0.41
    જી
    0.38
     Sterling
    0.37
    modified
    0.37
     बयान
    0.36
     Stirling
    0.35
     pem
    0.35
     Sta
    0.35
     Thi
    0.34
    Pont
    0.34
    Activations Density 0.000%

    No Known Activations