© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2790
    Prev
    Next
    INDEX
    Explanations

    words and phrases that commonly appear in email or other messaging-related content, especially related to scheduling and address books.

    oai_token-act-pair · gemini-2.0-flash

    importing/exporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.59
    Tikang
    -0.54
    ReusableCell
    -0.53
    webElementXpaths
    -0.53
     kaarangay
    -0.52
    UnsafeEnabled
    -0.51
     extremos
    -0.50
    ppan
    -0.49
    ьаж
    -0.47
    Referencie
    -0.45
    POSITIVE LOGITS
     import
    2.11
     importing
    1.91
     export
    1.91
     Import
    1.84
     imports
    1.80
     imported
    1.72
     exporting
    1.70
     Importing
    1.70
    Import
    1.63
     importer
    1.63
    Activations Density 2.615%

    No Known Activations