© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175198
    Prev
    Next
    INDEX
    Explanations

    danger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     erg
    0.41
    媺
    0.40
    za
    0.39
     écart
    0.39
    egos
    0.38
    0.38
     biv
    0.37
     Trabal
    0.37
     เรา
    0.36
    न्द
    0.36
    POSITIVE LOGITS
     natoque
    0.42
    ைகளைப்
    0.40
     Gin
    0.39
    松
    0.39
    四大
    0.38
     松
    0.37
    Gin
    0.37
    ﺧ
    0.36
    BoardManager
    0.36
    িয়াস
    0.35
    Activations Density 0.003%

    No Known Activations