© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208813
    Prev
    Next
    INDEX
    Explanations

    calculation

    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_10_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
    јединачна
    0.77
     ursprüng
    0.76
     ihren
    0.66
    귿
    0.65
    <unused692>
    0.62
    伌
    0.61
     uzun
    0.60
    一百
    0.59
     deinen
    0.59
    <unused445>
    0.59
    POSITIVE LOGITS
    ↵
    0.80
    "
    0.72
     set
    0.71
     science
    0.67
     newspaper
    0.63
     hear
    0.62
     chemistry
    0.62
     snippet
    0.62
     be
    0.61
     journalism
    0.61
    Activations Density 0.001%

    No Known Activations