© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1444
    Prev
    Next
    INDEX
    Explanations

    words corresponding to scientific and technical vocabulary, particularly in the area of biology

    oai_token-act-pair · gemini-2.0-flash

    flies and sanitation

    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
    Autoritní
    -0.70
    WebElementEntity
    -0.69
     AssemblyCulture
    -0.68
    expandindo
    -0.68
    transQ
    -0.66
     defaultstate
    -0.65
    )"),
    -0.65
    TypedDataSet
    -0.64
     otomatig
    -0.64
    MigrationBuilder
    -0.62
    POSITIVE LOGITS
     undef
    0.53
    caten
    0.47
     فريبيس
    0.47
    hydrat
    0.44
    chle
    0.44
     محفوظة
    0.43
    johtaja
    0.43
    şekkür
    0.42
    Analysts
    0.41
    luigi
    0.41
    Activations Density 10.751%

    No Known Activations