© 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. 195388
    Prev
    Next
    INDEX
    Explanations

    Prior knowledge schema

    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
    ፈጥ
    0.40
     트리플
    0.39
    锁
    0.38
     Institutional
    0.38
     AMAZ
    0.36
     institutional
    0.35
    柇
    0.35
     判断
    0.35
    isini
    0.34
    രണ
    0.34
    POSITIVE LOGITS
     schema
    1.11
     Schema
    0.97
     sche
    0.95
     prior
    0.93
    schema
    0.93
    Schema
    0.90
     background
    0.89
     schemas
    0.88
    prior
    0.85
    Prior
    0.84
    Activations Density 0.002%

    No Known Activations