© 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. 200969
    Prev
    Next
    INDEX
    Explanations

    places and 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
    Not in Any Lists

    No Comments

    Negative Logits
     stone
    1.20
     Stone
    1.07
    Stone
    0.98
    石
    0.95
     STONE
    0.92
    stone
    0.91
     foundations
    0.82
     камен
    0.80
     foundation
    0.80
     ston
    0.77
    POSITIVE LOGITS
     चैंपियन
    0.43
     हाईकोर्ट
    0.38
    йки
    0.38
    spiele
    0.38
    朓
    0.37
    ണ്ഡ
    0.36
     شپ
    0.36
     سانت
    0.36
     Polonia
    0.36
    offsetHeight
    0.35
    Activations Density 0.041%

    No Known Activations