© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77562
    Prev
    Next
    INDEX
    Explanations

    character roles or archetypes

    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_29_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
     (|
    0.41
     facie
    0.39
     cout
    0.38
    SIE
    0.38
     constituting
    0.38
    šće
    0.37
     معنى
    0.37
    visually
    0.36
     diffe
    0.36
    awa
    0.35
    POSITIVE LOGITS
    usste
    0.38
     advocacy
    0.38
    GPS
    0.38
    Repl
    0.37
    งาน
    0.37
    ᆨ
    0.36
     gossip
    0.36
    CSV
    0.35
    Absent
    0.35
     balans
    0.35
    Activations Density 0.004%

    No Known Activations