© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6750
    Prev
    Next
    INDEX
    Explanations

    various bits of computer code, including code syntax and comments.

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax elements and controls

    np_token-act-pair-logits · gpt-4o-mini

    semicolon/parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    <strong>
    -0.70
    1
    -0.65
    2
    -0.65
    (
    -0.63
    <em>
    -0.62
    9
    -0.61
    +
    -0.60
    0
    -0.60
    [
    -0.59
    !
    -0.59
    POSITIVE LOGITS
    expandindo
    1.34
    NameInMap
    1.32
    StoryboardSegue
    1.31
     ModelExpression
    1.25
    featureID
    1.23
    RenderAtEndOf
    1.19
     <=",
    1.16
     فريبيس
    1.16
    TagMode
    1.14
     kasarigan
    1.13
    Activations Density 3.029%

    No Known Activations