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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5427
    Prev
    Next
    INDEX
    Explanations

    code that contains colons, parentheses, commas, ampersands, the word "value", and the word "return"

    oai_token-act-pair · gemini-2.0-flash

    Code and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AttributeSet
    -0.52
    ddar
    -0.50
    lunda
    -0.50
    onimo
    -0.50
     traffic
    -0.49
    $_['
    -0.49
     carica
    -0.49
    AccessControl
    -0.49
    ertes
    -0.48
     [[
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.93
     للاسماء
    0.62
    KommentareTeilen
    0.57
     &___
    0.54
    FlatList
    0.53
    Hochspringen
    0.50
     يتيمه
    0.50
    #+#
    0.50
     rhestr
    0.49
    include
    0.48
    Activations Density 1.730%

    No Known Activations