© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 7030
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     bittern
    0.29
    न्देल
    0.29
    <unused22>
    0.29
     treatise
    0.29
     caliper
    0.28
     حي
    0.27
    üllen
    0.27
     valentine
    0.27
     مِن
    0.27
     valentines
    0.27
    POSITIVE LOGITS
    황
    0.25
    Albert
    0.25
    sl
    0.23
    arna
    0.23
     SDN
    0.23
    VJ
    0.23
     deformation
    0.23
     sl
    0.23
     Rodriguez
    0.22
    Franc
    0.22
    Activations Density 0.001%

    No Known Activations