© 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. 142556
    Prev
    Next
    INDEX
    Explanations

    programming optimization

    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
     FPGA
    0.45
     Pascal
    0.41
     NPV
    0.40
    𝙪
    0.39
     pascal
    0.39
    算法
    0.38
    ော
    0.38
     онлайн
    0.38
     fine
    0.38
     بنایا
    0.38
    POSITIVE LOGITS
    赦
    0.39
    isins
    0.38
    putBoolean
    0.38
    㤟
    0.37
    carboxylate
    0.37
    кономски
    0.37
     razum
    0.37
    خاب
    0.36
    GEORGE
    0.36
    mercial
    0.36
    Activations Density 0.001%

    No Known Activations