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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30639
    Prev
    Next
    INDEX
    Explanations

    archaic contractions like 'tis and 'neath

    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_31_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
    even
    0.36
    new
    0.33
    -\{
    0.33
    simulate
    0.33
    var
    0.32
    if
    0.31
    yes
    0.31
    content
    0.31
    sometimes
    0.31
    although
    0.31
    POSITIVE LOGITS
     bore
    0.33
     aire
    0.32
     bonds
    0.31
     masaje
    0.31
    ꉂ
    0.31
     ont
    0.31
    🏽
    0.30
     ler
    0.30
     signes
    0.30
     pue
    0.30
    Activations Density 0.013%

    No Known Activations