© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1600
    Prev
    Next
    INDEX
    Explanations

    uses of the words "and", "or", "is", "has", or other related words in sentences

    oai_token-act-pair · gemini-2.0-flash

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Geplaatst
    -1.09
     disambiguazione
    -0.98
     betweenstory
    -0.89
    webElement
    -0.83
     saites
    -0.82
     виправивши
    -0.82
    KommentareTeilen
    -0.82
     HasFactory
    -0.81
    Viitteet
    -0.79
    ItemBackground
    -0.78
    POSITIVE LOGITS
     alatt
    0.47
    om
    0.47
    gen
    0.47
     convaincre
    0.44
    után
    0.44
     respectively
    0.44
     mourir
    0.43
     trade
    0.43
     since
    0.43
    óta
    0.43
    Activations Density 1.572%

    No Known Activations