© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30960
    Prev
    Next
    INDEX
    Explanations

    California locations

    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_50_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
     Kull
    0.39
    蘆
    0.38
     Safran
    0.38
     Peacock
    0.36
     הט
    0.35
    ">=</
    0.35
     faulted
    0.35
    ਡ
    0.35
     சொன்ன
    0.34
    Tas
    0.34
    POSITIVE LOGITS
     Mont
    0.54
    Mont
    0.52
    Antonio
    0.48
     António
    0.46
     Antonio
    0.46
     Pillar
    0.44
     bon
    0.42
     pillar
    0.42
     Merkez
    0.40
    Princeton
    0.39
    Activations Density 0.001%

    No Known Activations