© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14595
    Prev
    Next
    INDEX
    Explanations

    language from legal documents along with the names and titles of people in the court system

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     title
    -0.49
     Paglinawan
    -0.48
     Gro
    -0.48
    tsk
    -0.46
     grab
    -0.45
     Grab
    -0.45
     grabbing
    -0.44
    ::::::::
    -0.44
    Grab
    -0.44
     titled
    -0.43
    POSITIVE LOGITS
     resourceCulture
    0.76
     سكانية
    0.75
     Daß
    0.75
     Majefty
    0.69
     ExecuteAsync
    0.68
    $}}
    0.67
    مصادر
    0.66
    oarece
    0.65
     Archiproducts
    0.65
     Drapeau
    0.64
    Activations Density 1.441%

    No Known Activations