© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148276
    Prev
    Next
    INDEX
    Explanations

    writing articles

    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_23_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
    ולוג
    0.30
    
    0.26
     bibendum
    0.25
    starcore
    0.25
    omeres
    0.25
     ción
    0.25
     lipids
    0.25
    ӵ
    0.25
    িয়ান
    0.24
    everyone
    0.24
    POSITIVE LOGITS
    Fusion
    0.28
     Fusion
    0.28
     almost
    0.25
     Establishment
    0.24
     Influ
    0.24
     почти
    0.24
     Head
    0.23
    Wak
    0.23
    fusion
    0.23
     hampir
    0.23
    Activations Density 0.004%

    No Known Activations