© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    code snippets including the words "license," "file," or "package"

    oai_token-act-pair · gemini-2.0-flash

    PHP code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -0.68
    Geplaatst
    -0.62
     "];
    -0.57
    guenos
    -0.55
     jadx
    -0.54
    berdayakan
    -0.54
     conmigo
    -0.53
     giustizia
    -0.52
    <bos>
    -0.52
    perasi
    -0.52
    POSITIVE LOGITS
    :✨
    0.70
    Izvori
    0.63
    Personensuche
    0.59
    webElementXpaths
    0.57
    AsUp
    0.57
     Leid
    0.56
     дописавши
    0.54
    AutoScale
    0.53
    Hentet
    0.52
     Lin
    0.52
    Activations Density 3.995%

    No Known Activations