© 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. 33668
    Prev
    Next
    INDEX
    Explanations

    georgia

    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
     Georgian
    0.37
    ခြေ
    0.37
    unnels
    0.34
    Georgian
    0.34
     சப
    0.33
    粮
    0.33
    ສາ
    0.32
     Georgia
    0.32
    }}}-\
    0.32
     flood
    0.31
    POSITIVE LOGITS
     soff
    0.35
     फोन
    0.34
     massless
    0.33
    MAD
    0.33
     फ़ोन
    0.33
    ότητας
    0.33
    ್ರಾ
    0.32
     setActive
    0.32
    Metall
    0.32
     IRAS
    0.32
    Activations Density 0.001%

    No Known Activations