© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    astronomy and scientific units

    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
    েত্রে
    0.36
    Rocks
    0.36
     Dijk
    0.36
    あれ
    0.34
    ала
    0.34
    Trail
    0.33
    FLOAT
    0.32
    Occupation
    0.32
    䀖
    0.32
    伀
    0.31
    POSITIVE LOGITS
     കഴിഞ്ഞ
    0.33
     Magazine
    0.32
     manejo
    0.31
     transcript
    0.30
    mensagem
    0.30
     magazine
    0.29
    mensaje
    0.29
     ouvrage
    0.29
     Cabernet
    0.29
     Beograd
    0.29
    Activations Density 0.000%

    No Known Activations