© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6903
    Prev
    Next
    INDEX
    Explanations

    words related to official documentation, especially legal documents and certificates related to identity and citizenship

    oai_token-act-pair · gemini-2.0-flash

    elements of programming or code syntax

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

    forms

    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
    DockStyle
    -0.52
    postIndex
    -0.50
     تضيفلها
    -0.50
    contentLoaded
    -0.47
     Wied
    -0.45
    expandindo
    -0.44
    ंदीखरीदारी
    -0.44
    thenReturn
    -0.41
    gsmål
    -0.41
     standing
    -0.40
    POSITIVE LOGITS
    <!--[
    0.69
    ArgsConstructor
    0.67
    :✨
    0.65
    ORIGINAL
    0.63
    /*
    0.59
     EventArgs
    0.58
    yssey
    0.57
    $​
    0.57
    IsMutable
    0.56
     scanned
    0.54
    Activations Density 1.536%

    No Known Activations