© 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. 45769
    Prev
    Next
    INDEX
    Explanations

    base words, attention, confidence

    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
     (
    0.18
    自分の
    0.18
    倆
    0.18
    kg
    0.18
    ようやく
    0.18
    local
    0.17
     Humanos
    0.17
    関連
    0.17
    row
    0.17
    ਣਾ
    0.17
    POSITIVE LOGITS
    ස
    0.21
    يرا
    0.21
     zwią
    0.21
     shouldUse
    0.19
    áne
    0.19
     will
    0.19
     posséd
    0.19
     entered
    0.19
    áját
    0.19
    azität
    0.19
    Activations Density 0.003%

    No Known Activations