© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170822
    Prev
    Next
    INDEX
    Explanations

    names or titles

    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_20_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
    Má
    0.19
    姓
    0.18
    Ngày
    0.18
    Ϲ
    0.17
    Muito
    0.17
    गली
    0.17
     Phạm
    0.17
    rendo
    0.17
     século
    0.17
     filhos
    0.17
    POSITIVE LOGITS
     объем
    0.19
     =
    0.18
    7
    0.18
     pursues
    0.18
     относится
    0.17
     によって
    0.17
    6
    0.17
     theoretically
    0.17
    ∈</
    0.17
     gaseous
    0.16
    Activations Density 0.001%

    No Known Activations