© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69539
    Prev
    Next
    INDEX
    Explanations

    specific concepts

    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_46_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
     институ
    0.48
    institutional
    0.45
     institutional
    0.44
    Institutional
    0.42
     Institutional
    0.42
     institution
    0.39
    English
    0.39
     институт
    0.39
     창
    0.39
     non
    0.38
    POSITIVE LOGITS
     Abo
    0.40
    姉
    0.40
     Minimalism
    0.40
     Mans
    0.39
     GRAPH
    0.39
     Rising
    0.38
    酢
    0.37
     minimalism
    0.37
     HA
    0.36
     spic
    0.36
    Activations Density 0.057%

    No Known Activations