© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82051
    Prev
    Next
    INDEX
    Explanations

    PrimaryKey and individuals

    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_0_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
     to
    1.92
     by
    1.37
    <0x80>
    1.34
    ยัง
    1.15
     불구하고
    1.13
     musical
    1.12
     extracurricular
    1.12
    áš
    1.11
     at
    1.09
     arrond
    1.04
    POSITIVE LOGITS
    ни
    1.90
    ا
    1.71
    ா
    1.45
    는
    1.45
    다
    1.43
    א
    1.39
    ام
    1.37
    и
    1.34
    の結果
    1.32
    Б
    1.30
    Activations Density 0.001%

    No Known Activations