© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154536
    Prev
    Next
    INDEX
    Explanations

    foreign key references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ovjek
    0.37
    ended
    0.37
    arbeitet
    0.35
     закончи
    0.35
    中古
    0.35
     narc
    0.35
    ముల
    0.35
    ኖች
    0.34
    🐪
    0.34
     》
    0.34
    POSITIVE LOGITS
     یکی
    0.42
     έναν
    0.40
     eikä
    0.39
     Supervis
    0.39
     maß
    0.39
     surprises
    0.38
     schemas
    0.38
     promiscu
    0.38
     যা
    0.36
     adı
    0.36
    Activations Density 0.001%

    No Known Activations