© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121536
    Prev
    Next
    INDEX
    Explanations

    initializing code or data structures

    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_27_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
    趟
    0.42
    循
    0.38
     cpt
    0.38
    が出
    0.38
    вший
    0.37
    层面
    0.37
     שה
    0.36
    的高
    0.36
    upra
    0.36
    --*/
    0.36
    POSITIVE LOGITS
     المعلومات
    0.42
     enemies
    0.42
     Informations
    0.41
    INFORMATION
    0.41
    聶
    0.40
     informações
    0.39
     uninformed
    0.39
     informations
    0.38
     horrors
    0.38
     serp
    0.38
    Activations Density 0.001%

    No Known Activations