© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    mentions of legends in figures, likely in the context of scientific data plots

    oai_token-act-pair · gemini-2.0-flash

    legend

    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
    #+#
    -0.69
    <bos>
    -0.69
    UseVisualStyle
    -0.69
    WebServlet
    -0.69
    webElementXpaths
    -0.69
    PreExecute
    -0.68
     kasarigan
    -0.68
    Abitanti
    -0.68
    lidean
    -0.67
    تقاوى
    -0.67
    POSITIVE LOGITS
    rawDesc
    0.60
    udur
    0.56
     profils
    0.53
    opinions
    0.53
     ureter
    0.52
     abstrato
    0.52
    adır
    0.51
     Rois
    0.50
    cold
    0.49
    ยว
    0.49
    Activations Density 0.546%

    No Known Activations