© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36884
    Prev
    Next
    INDEX
    Explanations

    say "ing" pattern

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loor
    0.37
     gep
    0.37
     ず
    0.36
    秇
    0.36
    dfs
    0.35
     dp
    0.35
    abh
    0.35
    UBE
    0.34
    릿
    0.34
    Gre
    0.34
    POSITIVE LOGITS
     fling
    1.86
     sling
    1.79
     Sling
    1.69
    fling
    1.68
    sling
    1.63
     slings
    1.52
     fl
    1.47
     flung
    1.41
     sl
    1.40
    fl
    1.23
    Activations Density 0.005%

    No Known Activations