© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161209
    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_31_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
     بک
    0.37
    撼
    0.37
    羵
    0.35
     trol
    0.35
    Տ
    0.35
     വിള
    0.35
     JUSTICE
    0.34
    ܢ
    0.34
     COND
    0.34
     Kür
    0.34
    POSITIVE LOGITS
    cip
    0.44
    oser
    0.38
     Oscar
    0.37
    сре
    0.36
    нося
    0.34
     Repert
    0.34
    Oscar
    0.33
    டர்
    0.33
    ossal
    0.33
    putBoolean
    0.33
    Activations Density 0.000%

    No Known Activations