© 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. 141907
    Prev
    Next
    INDEX
    Explanations

    code; VBA

    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
    <s>
    0.44
    NUMBER
    0.42
    Prior
    0.42
     Prior
    0.37
    Celtic
    0.37
     defe
    0.37
     head
    0.36
     Celtic
    0.36
    COVER
    0.36
    GLAND
    0.35
    POSITIVE LOGITS
    ពេ
    0.40
    ıza
    0.39
    诠
    0.38
     св
    0.37
    ্যান্ট
    0.36
    letak
    0.36
     tumhe
    0.36
     aseguró
    0.36
     aumentó
    0.36
     পরস্প
    0.36
    Activations Density 0.003%

    No Known Activations