© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    rolling eyes

    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_13_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
    áš
    0.62
    withtag
    0.57
    㮔
    0.55
     itens
    0.54
     atyp
    0.52
     Gilman
    0.52
    
    0.52
    螈
    0.52
    äk
    0.51
    áž
    0.50
    POSITIVE LOGITS
    pent
    0.52
    Do
    0.51
    DDD
    0.50
    Capt
    0.50
    CAPT
    0.48
    rovers
    0.46
    Naive
    0.46
    bucks
    0.46
    apek
    0.46
    Dü
    0.45
    Activations Density 0.023%

    No Known Activations