© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18165
    Prev
    Next
    INDEX
    Explanations

    `set`, `Host`, `read`, `FORM`, `:=`

    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_15_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
    郡
    0.15
    स्थ्य
    0.12
    Encoding
    0.12
    μέν
    0.12
     канторы
    0.12
     وګټ
    0.12
    认可
    0.12
    곤
    0.12
    企
    0.12
    优
    0.12
    POSITIVE LOGITS
     Ships
    0.14
     Resistance
    0.13
    /////////
    0.13
    radiol
    0.12
     dinâmica
    0.12
    riso
    0.12
    আমাদের
    0.12
    রামর্শ
    0.12
    ships
    0.11
     Sulawesi
    0.11
    Activations Density 0.152%

    No Known Activations