© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9036
    Prev
    Next
    INDEX
    Explanations

    historical descriptions of the invention or development of a technology or medical process

    oai_token-act-pair · gemini-2.0-flash

    inventions

    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
     development
    -3.13
     Development
    -2.83
    Development
    -2.80
    development
    -2.73
     DEVELOPMENT
    -2.52
     Entwicklung
    -2.27
     develop
    -2.25
    DEVELOPMENT
    -2.17
     Develop
    -2.14
    develop
    -2.14
    POSITIVE LOGITS
    adpleegd
    0.60
     calldata
    0.58
    catraz
    0.57
    жешь
    0.56
    Tikang
    0.51
    AddHtmlAttribute
    0.50
     postIndex
    0.49
    دانشنامهٔ
    0.49
     khỏi
    0.48
    XmlRootElement
    0.47
    Activations Density 5.947%

    No Known Activations