© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200093
    Prev
    Next
    INDEX
    Explanations

    Baltic states

    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_15_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
    azität
    0.52
    ولو
    0.51
    ці
    0.50
    عدد
    0.49
    сло
    0.49
    暝
    0.49
    wavelength
    0.48
    戦略
    0.48
    )}}\
    0.48
     Será
    0.48
    POSITIVE LOGITS
     הזה
    0.52
     pep
    0.52
     essence
    0.50
     zyg
    0.48
     thigh
    0.47
     defraud
    0.46
     perforation
    0.46
    धिका
    0.46
     puncture
    0.45
     nicotine
    0.45
    Activations Density 0.001%

    No Known Activations