© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48294
    Prev
    Next
    INDEX
    Explanations

    Jupyter Notebook

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warten
    0.36
    elson
    0.36
     ხელ
    0.35
    جور
    0.35
     kolek
    0.34
    配
    0.34
     عيد
    0.34
    ⴳ
    0.34
     zo
    0.34
     onerror
    0.33
    POSITIVE LOGITS
     Jupyter
    0.41
    வு
    0.36
     sympy
    0.36
     Butler
    0.35
     swept
    0.34
     inefficient
    0.34
     Documentation
    0.34
    Simpl
    0.33
    Documentation
    0.33
     documentation
    0.33
    Activations Density 0.008%

    No Known Activations