© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3677
    Prev
    Next
    INDEX
    Explanations

    HTML unordered lists and table elements, especially those used in Javadoc-generated documentation.

    oai_token-act-pair · gemini-2.0-flash

    ul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -2.06
    AndEndTag
    -1.55
    Personensuche
    -1.40
    abestanden
    -1.36
    IUrlHelper
    -1.32
     cherchés
    -1.29
    sizeCache
    -1.27
    InjectAttribute
    -1.27
    DockStyle
    -1.25
    rungsseite
    -1.24
    POSITIVE LOGITS
     les
    0.68
     in
    0.67
     extra
    0.61
     sur
    0.60
    ri
    0.60
    /
    0.60
     R
    0.60
     or
    0.60
     a
    0.59
     an
    0.59
    Activations Density 0.647%

    No Known Activations