© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8150
    Prev
    Next
    INDEX
    Explanations

    snippets of code in (probably) Portuguese, specifically referencing streams and data transformation

    oai_token-act-pair · gemini-2.0-flash

    Portuguese language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Datuak
    -1.12
    KommentareTeilen
    -1.06
     disambiguazione
    -1.05
    Diwedd
    -1.03
    GEBURTSDATUM
    -1.02
    Rüyada
    -0.91
     ब्रेकडाउन
    -0.90
    SharedDtor
    -0.83
     nahilalakip
    -0.82
     allAfrica
    -0.82
    POSITIVE LOGITS
     the
    0.88
     The
    0.71
     I
    0.68
     it
    0.66
    ,
    0.64
     you
    0.63
    '
    0.61
     and
    0.59
     la
    0.59
     It
    0.59
    Activations Density 0.187%

    No Known Activations