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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15372
    Prev
    Next
    INDEX
    Explanations

    articles and common words associated with questions or problem solving

    oai_token-act-pair · gemini-2.0-flash

    software versions

    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
     négociations
    -0.94
     genoux
    -0.93
     vœux
    -0.93
     pouvoirs
    -0.91
     attentes
    -0.91
     épaules
    -0.90
     bienfaits
    -0.89
     prochaines
    -0.88
     bénéfices
    -0.88
     intérêts
    -0.83
    POSITIVE LOGITS
     ones
    1.10
     mga
    0.91
    ographies
    0.88
     những
    0.86
     versions
    0.82
     models
    0.81
     embodiments
    0.80
     IPs
    0.80
     counterparts
    0.77
     locales
    0.76
    Activations Density 8.530%

    No Known Activations