© 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. 74494
    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
    headers
    0.38
    தேச
    0.38
    டக்கலை
    0.38
    __':
    0.36
    бен
    0.36
    RODUCTION
    0.35
    hean
    0.35
    pkey
    0.35
    pym
    0.35
    簍
    0.34
    POSITIVE LOGITS
     Ruskin
    0.36
    Cp
    0.35
     голу
    0.34
     Fake
    0.33
     ях
    0.33
     흐
    0.32
    坐
    0.32
     biking
    0.32
     reckon
    0.32
     Bach
    0.32
    Activations Density 0.000%

    No Known Activations