© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9804
    Prev
    Next
    INDEX
    Explanations

    statements of funding, authorship, data availability and acknowledgements in research papers.

    oai_token-act-pair · gemini-2.0-flash

    acknowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Himo
    -0.67
    Hauptartikel
    -0.66
     AssemblyCulture
    -0.66
    createTextNode
    -0.64
    viaf
    -0.61
    ecore
    -0.60
     setError
    -0.59
    ethene
    -0.59
     KeyError
    -0.59
     Catania
    -0.58
    POSITIVE LOGITS
    <bos>
    1.14
    AddTagHelper
    0.67
    /*
    0.50
    verwijspagina
    0.48
     grazie
    0.47
    while
    0.46
    dat
    0.45
    n
    0.44
    Šaltiniai
    0.44
     ffilmiau
    0.44
    Activations Density 2.428%

    No Known Activations