© 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. 30902
    Prev
    Next
    INDEX
    Explanations

    model parameters

    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
    ǎng
    0.38
    լ
    0.38
    ariales
    0.37
    lication
    0.37
    ımı
    0.36
    annt
    0.36
    idenza
    0.36
    ামীর
    0.36
    ARIO
    0.36
    örung
    0.36
    POSITIVE LOGITS
     Yeon
    0.38
     ge
    0.37
     Ge
    0.36
     cellar
    0.35
    GetComponent
    0.35
    指
    0.34
     నె
    0.34
     scientists
    0.33
     Alfred
    0.33
     multicolor
    0.33
    Activations Density 0.001%

    No Known Activations