Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1131
    Prev
    Next
    INDEX
    Explanations

    measurements and processes in the description of lab experiments

    oai_token-act-pair · gemini-2.0-flash

    technical documents containing measurements and variables

    np_token-act-pair-logits · gemini-2.0-flash

    science and engineering text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    TestingModule
    -0.78
     الحره
    -0.63
    aktery
    -0.59
     intérieure
    -0.57
     vectoriales
    -0.55
     indépendant
    -0.54
     spéciaux
    -0.54
     supérieurs
    -0.54
     <=",
    -0.54
    IsContent
    -0.53
    POSITIVE LOGITS
    Personensuche
    0.59
     rhestr
    0.57
     Surname
    0.54
    endphp
    0.54
     &___
    0.50
    ütter
    0.49
    verwijspagina
    0.48
    lactin
    0.46
    $_['
    0.45
    ergies
    0.45
    Activations Density 4.429%

    No Known Activations