© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14843
    Prev
    Next
    INDEX
    Explanations

    text related to economics, such as prices, inflation, and monetary policy.

    oai_token-act-pair · gemini-2.0-flash

    Financial news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ViewFeatures
    -0.80
    chiato
    -0.53
    kloped
    -0.52
    setDo
    -0.49
    rdom
    -0.49
     gelijk
    -0.49
     nonatomic
    -0.49
    ۜ
    -0.48
    мпер
    -0.48
    olesome
    -0.48
    POSITIVE LOGITS
     CME
    0.57
    XmlType
    0.57
    出版年
    0.48
    ContentAsync
    0.47
     BBB
    0.46
     CIC
    0.46
     htt
    0.46
     CreateTagHelper
    0.46
     SOP
    0.45
     CEC
    0.45
    Activations Density 14.619%

    No Known Activations