© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17421
    Prev
    Next
    INDEX
    Explanations

    research and innovation

    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_15_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
     sabotage
    0.49
    🦖
    0.43
     Jacobson
    0.41
    frid
    0.41
    科学
    0.41
     appendices
    0.41
     dBASE
    0.40
     EN
    0.40
    헙
    0.40
     Keyes
    0.39
    POSITIVE LOGITS
    us
    0.41
    ك
    0.41
    void
    0.39
    zigzag
    0.39
    ست
    0.39
    По
    0.39
    black
    0.38
    class
    0.38
    un
    0.38
    {
    0.37
    Activations Density 0.018%

    No Known Activations