© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6880
    Prev
    Next
    INDEX
    Explanations

    HTML image tags and form submission-related attributes

    oai_token-act-pair · gemini-2.0-flash

    Height

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     BoxFit
    -0.65
    FontOfSize
    -0.51
    usepackage
    -0.50
    WithIdentifier
    -0.48
     EdgeInsets
    -0.48
    nmgp
    -0.47
     BorderRadius
    -0.46
    func
    -0.46
     BorderSide
    -0.46
     semic
    -0.45
    POSITIVE LOGITS
    <bos>
    1.17
     समीक्षाओं
    0.88
     censiti
    0.82
    cerely
    0.71
    ---*/
    0.69
    ]--;
    0.66
    etheless
    0.66
    %");
    0.64
    IContainer
    0.63
    irited
    0.60
    Activations Density 3.932%

    No Known Activations