© 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. 1211
    Prev
    Next
    INDEX
    Explanations

    a wide variety of sentence fragments and discourse markers.

    oai_token-act-pair · gemini-2.0-flash

    Varies depending on condition

    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
     depending
    -2.83
    depending
    -2.55
     depends
    -2.30
    Depending
    -2.20
     Depending
    -2.20
     dependiendo
    -2.17
     Depends
    -2.09
    depends
    -2.03
    Depends
    -2.03
     depend
    -1.97
    POSITIVE LOGITS
    UAGE
    0.55
     corne
    0.54
    manship
    0.54
    Geografie
    0.54
    إنه
    0.52
     MwSt
    0.51
    onets
    0.51
     ProductService
    0.50
    makeConstraints
    0.50
    enegger
    0.49
    Activations Density 4.399%

    No Known Activations