© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139375
    Prev
    Next
    INDEX
    Explanations

    East–West dialogue and bridging gaps

    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_12_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
     suggests
    0.50
     approximating
    0.48
     sensiblement
    0.48
     analytically
    0.48
    自動車
    0.47
    mk
    0.47
    zeit
    0.46
    削
    0.46
     sugiere
    0.46
     прив
    0.46
    POSITIVE LOGITS
     Vara
    0.63
     CSI
    0.60
     SPI
    0.58
    вах
    0.54
     ساح
    0.53
     Hidden
    0.53
    ettha
    0.53
    zenes
    0.52
     Vaugh
    0.52
     Patio
    0.52
    Activations Density 0.000%

    No Known Activations