© 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. 201197
    Prev
    Next
    INDEX
    Explanations

    Capital of Indonesia

    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
     Ml
    0.40
     documentary
    0.38
     accent
    0.38
     सिंग
    0.38
    lng
    0.36
    carboxylic
    0.36
     kỳ
    0.35
    ਟੀ
    0.35
    {{
    0.35
    Ml
    0.35
    POSITIVE LOGITS
     CAPITAL
    0.46
     Capital
    0.42
     kapital
    0.42
     Capitals
    0.42
     vốn
    0.41
    хал
    0.40
    Capital
    0.40
     hout
    0.39
     Astr
    0.39
     capitalize
    0.39
    Activations Density 0.000%

    No Known Activations