© 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. 19235
    Prev
    Next
    INDEX
    Explanations

    infant symptoms

    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_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
     mutter
    0.55
    喃
    0.54
     mut
    0.52
    Mut
    0.50
     hablar
    0.50
     falar
    0.49
     staring
    0.49
     muttered
    0.48
    話
    0.47
     talking
    0.45
    POSITIVE LOGITS
     glTexCoord
    0.33
    წ
    0.33
    gpu
    0.32
    groupby
    0.31
     शिक्
    0.31
     წ
    0.30
     GPU
    0.30
     côn
    0.30
    吹き
    0.30
     വിമ
    0.30
    Activations Density 0.042%

    No Known Activations