© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46339
    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_22_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
     Testing
    0.48
    紥
    0.47
    gne
    0.46
    ぼ
    0.46
     taas
    0.46
    バン
    0.45
    턴
    0.44
     Service
    0.44
    綃
    0.44
    ボ
    0.44
    POSITIVE LOGITS
     وكان
    0.46
     pancreatitis
    0.45
     drows
    0.45
     onem
    0.45
    олові
    0.45
     заслу
    0.45
    మని
    0.44
     retinopathy
    0.44
     wouldn
    0.44
     другой
    0.44
    Activations Density 0.000%

    No Known Activations