© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14046
    Prev
    Next
    INDEX
    Explanations

    words associated with software code

    oai_token-act-pair · gemini-2.0-flash

    instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     instance
    -2.50
    instance
    -2.30
    Instance
    -2.22
     Instance
    -2.16
     instances
    -1.93
    INSTANCE
    -1.77
     INSTANCE
    -1.70
     Instances
    -1.62
    instances
    -1.56
     instancia
    -1.48
    POSITIVE LOGITS
     useEffect
    0.56
     avenge
    0.50
     Sénat
    0.47
    seasonal
    0.47
    sprogramm
    0.45
     doInBackground
    0.45
    Indexer
    0.45
    inverno
    0.45
     дома
    0.45
     pulumi
    0.45
    Activations Density 12.638%

    No Known Activations