© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2705
    Prev
    Next
    INDEX
    Explanations

    words or phrases commonly found in scientific publications.

    oai_token-act-pair · gemini-2.0-flash

    Research context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lèvres
    -0.75
     prochaines
    -0.73
     comportements
    -0.70
     larmes
    -0.69
     critères
    -0.64
     débats
    -0.62
     épaules
    -0.61
     attentes
    -0.60
     âmes
    -0.59
     vérit
    -0.59
    POSITIVE LOGITS
     batches
    0.91
     washes
    0.84
     harvests
    0.84
     wrecks
    0.81
     feasts
    0.81
     anchors
    0.80
     hashes
    0.79
     flasks
    0.79
     imports
    0.79
     shelters
    0.78
    Activations Density 27.779%

    No Known Activations