© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15355
    Prev
    Next
    INDEX
    Explanations

    code related to HTML checkboxes and possibly javascript

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    lowa
    -0.53
    Folks
    -0.51
    ={({
    -0.49
     folks
    -0.49
     RouterModule
    -0.49
    র্
    -0.48
    ubat
    -0.48
     Folks
    -0.48
     pres
    -0.45
    це
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.86
    ChildScrollView
    0.78
    +#+#
    0.73
    wapV
    0.73
    matchCondition
    0.73
    /*
    0.71
    AlterField
    0.69
     للمعارف
    0.67
    stdc
    0.66
    WebServlet
    0.66
    Activations Density 6.357%

    No Known Activations