© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206858
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     competition
    0.46
     Competition
    0.40
     Mé
    0.40
     demand
    0.39
     constant
    0.39
     leading
    0.39
    competition
    0.39
     сере
    0.39
     반
    0.39
     runners
    0.38
    POSITIVE LOGITS
    Presets
    0.40
    setProperty
    0.39
    ódulo
    0.38
    日本人
    0.38
    Rails
    0.38
     لہ
    0.38
    千年
    0.38
    ⬤
    0.37
    ₽
    0.37
    offline
    0.37
    Activations Density 0.000%

    No Known Activations