© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5988
    Prev
    Next
    INDEX
    Explanations

    monetary amounts including currency names

    oai_token-act-pair · gemini-2.0-flash

    currencies and amounts

    np_max-act-logits · gemini-2.0-flash

    money amounts (millions/billions)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     XCTest
    -0.79
    EndGlobalSection
    -0.73
     htmlFor
    -0.71
    XmlType
    -0.70
    indd
    -0.70
     مشين
    -0.69
    
    -0.68
    InjectAttribute
    -0.68
    viewDidLoad
    -0.66
    complexType
    -0.66
    POSITIVE LOGITS
     sopa
    0.47
     tenuta
    0.46
    toj
    0.43
     dores
    0.43
     bottes
    0.42
     le
    0.42
     dieren
    0.42
     sensibles
    0.42
     cargas
    0.42
     aufge
    0.42
    Activations Density 0.766%

    No Known Activations