© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10597
    Prev
    Next
    INDEX
    Explanations

    the word "audience"

    oai_token-act-pair · gemini-2.0-flash

    audience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     audience
    -1.10
    audience
    -1.01
     audiences
    -0.94
     autorytatywna
    -0.91
     snippetHide
    -0.89
     itſelf
    -0.84
     viewer
    -0.84
    Tembelea
    -0.82
    SBATCH
    -0.80
    Audience
    -0.80
    POSITIVE LOGITS
     Capital
    0.48
    acă
    0.47
     preceding
    0.45
     Advis
    0.43
     Future
    0.43
     Travel
    0.43
    fseek
    0.43
     sentencia
    0.42
     ago
    0.42
     ACT
    0.42
    Activations Density 0.489%

    No Known Activations