© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102600
    Prev
    Next
    INDEX
    Explanations

    Cybertruck and Starship

    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_16_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
    Lesson
    0.48
    पटना
    0.48
    ar
    0.46
    中学
    0.46
    स्
    0.45
    ശ്വാ
    0.44
    у
    0.44
     ți
    0.43
     refrigerator
    0.43
    {
    0.43
    POSITIVE LOGITS
     Eve
    0.52
     notificações
    0.52
     immunost
    0.49
     Elys
    0.47
     Camping
    0.47
     Spicer
    0.46
     Brazil
    0.46
     Brasil
    0.46
     Bush
    0.46
     când
    0.45
    Activations Density 0.003%

    No Known Activations