© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15498
    Prev
    Next
    INDEX
    Explanations

    phrases related to media production

    oai_token-act-pair · gemini-2.0-flash

    produce

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     EconPapers
    -0.82
    bootstrapcdn
    -0.74
     MainAxisSize
    -0.73
     aDecoder
    -0.66
    WebVitals
    -0.66
    ftagPool
    -0.65
     SqlDbType
    -0.63
    Personensuche
    -0.63
    بوابة
    -0.62
    __*/
    -0.62
    POSITIVE LOGITS
     producing
    1.70
     produce
    1.69
    produce
    1.57
     Producing
    1.54
     produced
    1.54
     produces
    1.52
    producing
    1.50
    Producing
    1.45
     Produce
    1.43
     producir
    1.38
    Activations Density 1.487%

    No Known Activations