© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10526
    Prev
    Next
    INDEX
    Explanations

    references to organizations related to health

    oai_token-act-pair · gemini-2.0-flash

    World Health Organization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Bauhaus
    -0.52
     lenker
    -0.52
    ThemeOverlay
    -0.51
    copal
    -0.50
    toHave
    -0.47
     Aki
    -0.45
     membrane
    -0.45
    potranspiration
    -0.45
     FAO
    -0.43
    MigrationBuilder
    -0.43
    POSITIVE LOGITS
     دیکھیے
    0.63
     للمعارف
    0.60
    WriteTagHelper
    0.59
    氓
    0.57
    gulama
    0.57
    -------------</
    0.55
    قایناق‌لار
    0.54
     Федерации
    0.53
     rubrique
    0.53
    Géographie
    0.53
    Activations Density 0.942%

    No Known Activations