© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206374
    Prev
    Next
    INDEX
    Explanations

    pronoun reference for people

    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_25_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
     }.
    0.39
     Tra
    0.38
    }.
    0.38
    anut
    0.37
     ome
    0.36
     '}
    0.36
    㷌
    0.36
    NFL
    0.35
     Savannah
    0.35
    .{
    0.35
    POSITIVE LOGITS
    院士
    0.43
     بتساوي
    0.42
     يساوي
    0.41
    については
    0.40
     മിക
    0.39
     miesięcy
    0.39
     precludes
    0.38
    രാഷ്ട്ര
    0.38
     പ്രസിഡ
    0.38
     nominal
    0.38
    Activations Density 0.002%

    No Known Activations