© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2039
    Prev
    Next
    INDEX
    Explanations

    words related to services, costs, and reimbursements

    oai_token-act-pair · gemini-2.0-flash

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zad
    -0.43
    roc
    -0.41
    HD
    -0.41
    moni
    -0.41
    Exposure
    -0.40
    mn
    -0.39
     Empty
    -0.39
     Arbe
    -0.39
    Empty
    -0.39
    if
    -0.38
    POSITIVE LOGITS
     nahilalakip
    1.27
     незавершена
    1.02
     للاسماء
    0.89
     autorytatywna
    0.88
    MigrationBuilder
    0.82
     defaultstate
    0.80
    expandindo
    0.80
    awtextra
    0.80
    InputBorder
    0.80
     doInBackground
    0.79
    Activations Density 1.134%

    No Known Activations