© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77251
    Prev
    Next
    INDEX
    Explanations

    natural locations, often whispered

    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_31_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
     Yucatan
    0.34
    மை
    0.32
    คม
    0.32
    SHADER
    0.32
     Yucatán
    0.31
     intégré
    0.31
     Є
    0.31
     integrand
    0.30
     integrated
    0.30
     Integrated
    0.29
    POSITIVE LOGITS
    addProduct
    0.32
     konie
    0.30
    탄소년단
    0.30
    ́u
    0.29
    황
    0.29
    <unused12>
    0.29
    ifferential
    0.28
    uds
    0.28
    óch
    0.28
     metast
    0.28
    Activations Density 0.003%

    No Known Activations