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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16172
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the military, aviation, and medicine, especially in a command, control, and regulatory context

    oai_token-act-pair · gemini-2.0-flash

    flight control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     kautta
    -0.50
     elä
    -0.47
     colpa
    -0.46
     varandra
    -0.45
     sähkö
    -0.44
     condamné
    -0.44
     sanitaires
    -0.44
    JsonNode
    -0.44
    äldrar
    -0.43
     religiosos
    -0.43
    POSITIVE LOGITS
     control
    1.00
     Control
    0.94
    Control
    0.87
    control
    0.85
     CONTROL
    0.81
    CONTROL
    0.81
     contrôle
    0.79
     controle
    0.76
     controllers
    0.71
    GraphicsUnit
    0.71
    Activations Density 2.017%

    No Known Activations