© 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. 194655
    Prev
    Next
    INDEX
    Explanations

    statistical terms

    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
    ავ
    0.38
    aville
    0.38
     fiabilité
    0.38
     subcluster
    0.37
    🧉
    0.37
    aronder
    0.37
    ברה
    0.36
    张
    0.36
    avon
    0.36
    elier
    0.35
    POSITIVE LOGITS
     Praise
    0.47
     Material
    0.42
     tala
    0.42
    боро
    0.40
     Hast
    0.39
     Crack
    0.39
     Missionary
    0.39
     Crete
    0.39
     Prompt
    0.38
    jde
    0.38
    Activations Density 0.000%

    No Known Activations