© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13313
    Prev
    Next
    INDEX
    Explanations

    trading and related business activities

    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_13_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
    %
    0.38
    ',
    0.35
    "
    0.35
    EO
    0.35
    UA
    0.34
    çe
    0.34
     کە
    0.34
    莺
    0.34
     संख्या
    0.34
     اله
    0.34
    POSITIVE LOGITS
     hráč
    0.35
    bend
    0.34
    κ
    0.34
    бер
    0.34
    мед
    0.34
    حده
    0.33
    빔
    0.33
     फांसी
    0.33
     annuities
    0.33
    periodic
    0.32
    Activations Density 0.006%

    No Known Activations