© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161425
    Prev
    Next
    INDEX
    Explanations

    specific scientific 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_31_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
     Miser
    0.33
    療法
    0.33
     데이터를
    0.32
     욕
    0.32
     YOUNG
    0.32
     그다
    0.31
    眼镜
    0.31
     NYSE
    0.30
    酭
    0.30
     agarr
    0.30
    POSITIVE LOGITS
     explan
    0.36
     encro
    0.34
     geographical
    0.34
     distract
    0.33
     path
    0.32
    iloc
    0.32
    path
    0.32
     decl
    0.32
    kW
    0.32
    oppel
    0.32
    Activations Density 0.001%

    No Known Activations