© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128878
    Prev
    Next
    INDEX
    Explanations

    SLAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    .
    1.05
    ového
    1.03
    0.95
    d
    0.93
    的东西
    0.88
    ความ
    0.87
    ৪
    0.83
    ig
    0.82
    高
    0.82
    使用
    0.81
    POSITIVE LOGITS
    ва
    1.35
    ные
    1.06
    いた
    1.02
    applique
    1.02
     می‌شود
    1.01
    ні
    0.99
     نمی‌
    0.98
    ‌ای
    0.98
    ‌های
    0.96
    vertices
    0.95
    Activations Density 0.001%

    No Known Activations