© 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. 68507
    Prev
    Next
    INDEX
    Explanations

    bottom

    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
     izquierda
    0.41
    itism
    0.40
    왼
    0.40
    左
    0.38
     left
    0.38
     structural
    0.37
     структур
    0.36
     structures
    0.35
    ")%>%
    0.35
     চাও
    0.35
    POSITIVE LOGITS
    down
    0.42
    DOWN
    0.42
     こんにちは
    0.41
    ண்ணா
    0.38
    Working
    0.38
    mover
    0.38
     ஒற்று
    0.38
    全市
    0.38
    灭
    0.38
    Up
    0.38
    Activations Density 0.001%

    No Known Activations