© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149490
    Prev
    Next
    INDEX
    Explanations

    My

    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_60_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
     team
    0.55
    Team
    0.50
    team
    0.50
    School
    0.42
     टीम
    0.42
     Team
    0.39
     an
    0.38
     a
    0.38
    Dog
    0.38
    Museum
    0.38
    POSITIVE LOGITS
     نام
    0.53
     Name
    0.51
     именем
    0.50
     Nombre
    0.50
    name
    0.49
    宠物
    0.48
    名稱
    0.47
     nama
    0.47
     NAME
    0.44
     pet
    0.44
    Activations Density 0.001%

    No Known Activations