© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206297
    Prev
    Next
    INDEX
    Explanations

    leader qualities and actions

    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_19_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
    angling
    0.36
    addKill
    0.36
    Hand
    0.34
    嫉
    0.33
    ussi
    0.33
    APA
    0.33
     \{
    0.33
    犹
    0.33
    Preliminary
    0.32
    USE
    0.32
    POSITIVE LOGITS
     sounded
    0.39
     meditative
    0.39
     thinker
    0.38
     iconic
    0.37
     outros
    0.36
     história
    0.36
     orator
    0.35
    ੌ
    0.35
     responsibility
    0.35
     gibt
    0.35
    Activations Density 0.013%

    No Known Activations