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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10597
    Prev
    Next
    INDEX
    Explanations

    words related to legal agreements between companies and customers

    oai_token-act-pair · gemini-2.0-flash

    users, customers, agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TypedDataSet
    -0.52
    kaart
    -0.49
    verwijspagina
    -0.47
     Worked
    -0.47
    haft
    -0.46
    汰
    -0.45
     stimm
    -0.44
    Linki
    -0.44
    جان
    -0.43
     entspricht
    -0.42
    POSITIVE LOGITS
     AssemblyVersion
    0.70
     AssemblyProduct
    0.65
    NgModule
    0.62
     Roskov
    0.58
    abestanden
    0.57
    IndentedString
    0.57
     NDEBUG
    0.57
    principalColumn
    0.56
     preuves
    0.56
     strconv
    0.55
    Activations Density 1.527%

    No Known Activations