© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205378
    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_10_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
    äure
    0.50
    鏄
    0.46
     concussion
    0.44
    、“
    0.44
    ドライバー
    0.43
    棄
    0.42
    derabad
    0.42
     Eclipse
    0.42
    噵
    0.42
    aclysm
    0.41
    POSITIVE LOGITS
     lean
    0.52
    р
    0.50
     nevoie
    0.47
     fondos
    0.47
     foe
    0.46
    בי
    0.46
    ুরে
    0.45
    лая
    0.44
     방향
    0.44
     Primavera
    0.44
    Activations Density 0.000%

    No Known Activations