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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16058
    Prev
    Next
    INDEX
    Explanations

    parts of legal contractual documents, specifically court filings with a plaintiff named Sithon suing Mercury

    oai_token-act-pair · gemini-2.0-flash

    Mentions "Sithon"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Mache
    -0.68
     Vise
    -0.68
     Gode
    -0.68
    henge
    -0.68
    chtete
    -0.66
     MUSE
    -0.65
     Pene
    -0.65
     barricade
    -0.65
     Rode
    -0.64
    rike
    -0.63
    POSITIVE LOGITS
    bein
    0.40
    teit
    0.40
     rédaction
    0.39
     Révolution
    0.38
     Pittsburgh
    0.37
    Minion
    0.37
    Kathryn
    0.37
     marchand
    0.36
     Northam
    0.36
    traversal
    0.36
    Activations Density 5.002%

    No Known Activations