© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8567
    Prev
    Next
    INDEX
    Explanations

    niece or nephew

    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_13_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
    前に
    0.30
     ভুট্টো
    0.26
    çe
    0.25
     Doncaster
    0.24
    멕
    0.24
     ਖ
    0.24
    setType
    0.24
     교통
    0.24
    覷
    0.23
    intu
    0.23
    POSITIVE LOGITS
     (!
    0.30
     יל
    0.30
    Children
    0.29
     children
    0.28
    children
    0.28
    rul
    0.26
     dedicado
    0.26
     дети
    0.26
     млад
    0.26
    르
    0.25
    Activations Density 0.007%

    No Known Activations