© 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. 200169
    Prev
    Next
    INDEX
    Explanations

    Roman

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nant
    0.36
    гээ
    0.35
     AUG
    0.34
     ACh
    0.34
     Gradle
    0.34
     Kubernetes
    0.34
     Georges
    0.34
    녜
    0.33
    neapolis
    0.33
     ceil
    0.33
    POSITIVE LOGITS
    哴
    0.39
    ीजन
    0.38
    '>
    0.37
     rab
    0.37
    袠
    0.37
    Mon
    0.37
    '`
    0.37
    '`,
    0.37
    economics
    0.36
    örper
    0.36
    Activations Density 0.002%

    No Known Activations