© 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. 19048
    Prev
    Next
    INDEX
    Explanations

    location prepositions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     विभ
    0.38
    ippy
    0.38
     그때
    0.38
     सर्वप्रथम
    0.37
    Dalam
    0.36
    ფორმა
    0.34
     مصر
    0.33
    夭
    0.33
    În
    0.32
    ထဲ
    0.32
    POSITIVE LOGITS
     tại
    1.53
     at
    1.52
    Tại
    1.15
     Tại
    1.08
     atthe
    0.87
     ณ
    0.75
     bei
    0.71
     chez
    0.70
    อยู่ที่
    0.70
     عند
    0.66
    Activations Density 0.095%

    No Known Activations