© 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. 257272
    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
     c
    0.48
     annual
    0.46
     pop
    0.44
     graduation
    0.44
     vibe
    0.44
     transition
    0.42
     specific
    0.42
     uncommon
    0.42
     পর
    0.41
     call
    0.40
    POSITIVE LOGITS
    餬
    0.56
    り
    0.55
    በ
    0.54
    蒌
    0.54
    рин
    0.54
    䛊
    0.54
    ری
    0.52
    𝗯
    0.52
    бры
    0.52
    ൯
    0.51
    Activations Density 0.000%

    No Known Activations