© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    do not generate

    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_40_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
     up
    0.50
     lên
    0.46
    ขึ้น
    0.45
    起来
    0.38
     വായി
    0.37
    Up
    0.37
    アップ
    0.37
    俐
    0.36
    өрд
    0.35
    @@]
    0.35
    POSITIVE LOGITS
     invent
    1.02
     inventing
    0.91
     invented
    0.88
     invention
    0.88
    invent
    0.79
     Invent
    0.78
     Invention
    0.75
     inventor
    0.72
    Invent
    0.71
     изобре
    0.71
    Activations Density 0.045%

    No Known Activations