© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19296
    Prev
    Next
    INDEX
    Explanations

    Indonesian places and names

    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_40_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
    巴士
    0.44
    lblName
    0.38
    MV
    0.38
    нето
    0.38
     letting
    0.36
    HH
    0.36
    lett
    0.36
    ēja
    0.36
    路线
    0.35
    ~~~
    0.35
    POSITIVE LOGITS
     Indonesian
    1.00
     इंडोनेशिया
    0.92
     indonesia
    0.89
     Indonesia
    0.89
     Indones
    0.87
    Indonesia
    0.87
     Jakarta
    0.80
     Yogyakarta
    0.80
     Jokowi
    0.79
    Jakarta
    0.76
    Activations Density 0.001%

    No Known Activations