© 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. 14758
    Prev
    Next
    INDEX
    Explanations

    import and related terms/concepts

    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
    机场
    0.41
     smě
    0.41
     ae
    0.38
     Airport
    0.38
     村
    0.37
     aeration
    0.37
     aggiunto
    0.37
    朝
    0.36
     transitions
    0.35
     Flughafen
    0.35
    POSITIVE LOGITS
     import
    2.34
     imported
    2.31
     Import
    2.20
    Import
    2.20
     importing
    2.20
     importation
    2.17
    import
    2.11
     imports
    2.11
     Importing
    2.11
     Imported
    2.09
    Activations Density 0.114%

    No Known Activations