© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202834
    Prev
    Next
    INDEX
    Explanations

    tests or trials

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Raghav
    0.42
     rebuild
    0.41
     pry
    0.41
     eventually
    0.38
    ि
    0.38
     leave
    0.37
     sometime
    0.37
     Pohl
    0.37
     burger
    0.37
     conferencing
    0.37
    POSITIVE LOGITS
    점
    0.43
    裨
    0.40
     Dependency
    0.40
     declaró
    0.38
    сайт
    0.38
     Points
    0.38
    ސް
    0.37
    Points
    0.37
    점이
    0.37
    Dependency
    0.37
    Activations Density 0.000%

    No Known Activations