© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39471
    Prev
    Next
    INDEX
    Explanations

    say "I'll"

    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_11_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
    With
    0.63
     revanche
    0.63
    o
    0.63
     TripAdvisor
    0.61
     With
    0.57
     http
    0.55
     आश्वासन
    0.55
    http
    0.55
     tranquilidad
    0.55
     वेतन
    0.54
    POSITIVE LOGITS
    вать
    0.64
    zé
    0.62
    simmons
    0.61
    ↵
    0.61
    ди
    0.61
    zę
    0.59
    си
    0.58
    
    0.57
    зь
    0.55
     Хар
    0.55
    Activations Density 0.001%

    No Known Activations