© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102917
    Prev
    Next
    INDEX
    Explanations

    bundle install

    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_14_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
    fireFlower
    0.57
    
    0.54
     AppMethodBeat
    0.53
    ❃
    0.52
    üğünüz
    0.51
    ड्रो
    0.51
    㞖
    0.51
     khán
    0.49
     upholstered
    0.49
     vv
    0.49
    POSITIVE LOGITS
    ity
    0.56
    _
    0.55
    L
    0.55
    level
    0.54
    Type
    0.51
     J
    0.50
    try
    0.50
    ή
    0.50
    os
    0.49
    Soup
    0.49
    Activations Density 0.001%

    No Known Activations