© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8442
    Prev
    Next
    INDEX
    Explanations

    sections relating to public health in scientific publications, especially the "PUBLIC HEALTH RELEVANCE" section and possibly results analysis

    oai_token-act-pair · gemini-2.0-flash

    academic/legal texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     specchio
    -0.58
     Voici
    -0.50
     yelek
    -0.50
    Personensuche
    -0.50
     essenziale
    -0.50
     ospiti
    -0.50
     esperti
    -0.49
     sguardo
    -0.49
    DISABLED
    -0.49
    nyttet
    -0.49
    POSITIVE LOGITS
     }}$}
    0.45
    neſs
    0.41
     getInt
    0.38
    leſs
    0.38
     iconFacebook
    0.37
    ível
    0.36
     BRARY
    0.36
    íveis
    0.36
    ++)
    
    0.35
    ORETICAL
    0.35
    Activations Density 2.667%

    No Known Activations