© 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. 12303
    Prev
    Next
    INDEX
    Explanations

    many common words and numbers, but also some words referencing organization or categorization and institutions.

    oai_token-act-pair · gemini-2.0-flash

    institutions/studies/laws

    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
    Companies
    -1.70
     companies
    -1.70
     businesses
    -1.59
     Companies
    -1.54
    Businesses
    -1.53
     organizations
    -1.51
    Organizations
    -1.48
     schools
    -1.48
    companies
    -1.48
     firms
    -1.46
    POSITIVE LOGITS
     Italijani
    0.64
    urlpatterns
    0.62
    RegressionTest
    0.61
    GetBytes
    0.57
     contextLoads
    0.56
     دیکھیے
    0.53
    QueryParams
    0.51
     समीक्षाओं
    0.50
    esez
    0.50
    tgz
    0.49
    Activations Density 4.542%

    No Known Activations