© 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. 337
    Prev
    Next
    INDEX
    Explanations

    language embeddings

    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
    RouterModule
    0.41
    Declared
    0.39
    SHARE
    0.39
     ಹು
    0.38
    Share
    0.37
    Abd
    0.37
    🦓
    0.37
    orra
    0.36
     Atr
    0.36
    neau
    0.35
    POSITIVE LOGITS
     Language
    0.46
     language
    0.46
     CB
    0.43
     LANGUAGE
    0.43
     Vin
    0.41
    пада
    0.40
    枃
    0.40
     Rare
    0.39
     Conjug
    0.39
     Count
    0.38
    Activations Density 0.019%

    No Known Activations