© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176650
    Prev
    Next
    INDEX
    Explanations

    dealers, platforms, companies

    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_20_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
    泓
    0.25
    ︰
    0.25
    、​
    0.24
     ство
    0.23
     anisot
    0.23
    传入
    0.23
     gravi
    0.23
     stali
    0.23
    
    0.22
     такой
    0.22
    POSITIVE LOGITS
     F
    0.27
     Door
    0.27
    dur
    0.26
     você
    0.26
    F
    0.26
    डोर
    0.25
     Information
    0.25
     Kapital
    0.24
    customer
    0.24
    dm
    0.24
    Activations Density 0.002%

    No Known Activations