© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143721
    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_46_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
     लिखने
    0.49
     writing
    0.48
     Writing
    0.47
     escribir
    0.47
     kirjo
    0.44
    Writing
    0.44
     لکھنے
    0.43
    writing
    0.42
     escrita
    0.42
    写
    0.41
    POSITIVE LOGITS
     recorded
    0.54
     Recorded
    0.54
    Recorded
    0.52
    recorded
    0.49
     recording
    0.46
     recordings
    0.45
     Recordings
    0.44
     Bahrain
    0.42
     име
    0.42
     Recorder
    0.42
    Activations Density 0.000%

    No Known Activations