© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 537
    Prev
    Next
    INDEX
    Explanations

    words related to upkeep and care, but also words related to finding things

    oai_token-act-pair · gemini-2.0-flash

    maintenance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     FetchType
    -0.46
    TintMode
    -0.43
    AddWithValue
    -0.42
    BackStack
    -0.42
     feu
    -0.41
    protoc
    -0.41
    URLException
    -0.40
     ap
    -0.40
     استنادى
    -0.40
    hafen
    -0.39
    POSITIVE LOGITS
     maintenance
    2.00
    maintenance
    1.80
     Maintenance
    1.77
    Maintenance
    1.77
     maint
    1.66
     maintained
    1.65
     maintain
    1.64
     upkeep
    1.63
    maintain
    1.63
     Maintain
    1.60
    Activations Density 0.993%

    No Known Activations