© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208958
    Prev
    Next
    INDEX
    Explanations

    say "had"

    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_56_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
    Tub
    0.43
     نړۍ
    0.42
     Η
    0.41
    තාව
    0.41
    Hen
    0.40
     কুট
    0.39
     ginh
    0.38
    oneph
    0.38
     हूं
    0.38
     نقول
    0.38
    POSITIVE LOGITS
     TDI
    0.46
     sepsis
    0.44
     PTI
    0.41
     RX
    0.38
     Sardinia
    0.38
     chord
    0.36
     sprayed
    0.36
    𝖽
    0.36
     produksi
    0.36
     EDI
    0.35
    Activations Density 0.000%

    No Known Activations