© 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. 1714
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup or table-like structures with dividers

    oai_token-act-pair · gemini-2.0-flash

    Special characters

    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
    -0.56
     surla
    -0.55
     nakalista
    -0.55
    TypedDataSet
    -0.54
    #+#
    -0.50
     ujednoznacz
    -0.50
    :✨
    -0.49
     nodeId
    -0.48
     ABV
    -0.48
     "..\..\..\
    -0.47
    POSITIVE LOGITS
    OOTDTY
    0.59
    complexContent
    0.55
    MigrationBuilder
    0.54
    EndInit
    0.52
     Sä
    0.50
    ablon
    0.49
    WebElementEntity
    0.48
    baz
    0.47
    Atsauces
    0.47
     Signalez
    0.46
    Activations Density 1.342%

    No Known Activations