© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    code, citations, or other document markup

    oai_token-act-pair · 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
    MLLoader
    -0.60
    SizeF
    -0.48
     competitive
    -0.47
    égek
    -0.45
     transfieras
    -0.43
     comparaison
    -0.43
     مق
    -0.43
     szem
    -0.41
    Iw
    -0.41
    addMouseListener
    -0.41
    POSITIVE LOGITS
    WithIOException
    0.76
     betweenstory
    0.69
    URLException
    0.65
    rizona
    0.62
    />";
    0.60
    HtmlAttribute
    0.59
    NameInMap
    0.58
    enumii
    0.57
     Ogil
    0.56
    Cyfeiriadau
    0.56
    Activations Density 68.377%

    No Known Activations