© 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. 16016
    Prev
    Next
    INDEX
    Explanations

    words related to data visualization in scientific contexts, like figures, plots, points, lines, dots, and diagrams.

    oai_token-act-pair · gemini-2.0-flash

    points

    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
    <bos>
    -0.66
     defaultstate
    -0.57
     arşivlendi
    -0.56
    期刊论文
    -0.56
    SBATCH
    -0.49
    ்கு
    -0.47
     AssemblyCompany
    -0.47
     وسلم
    -0.47
    -------------</
    -0.47
    rección
    -0.46
    POSITIVE LOGITS
    PointSize
    0.62
     centra
    0.58
    punkt
    0.58
     puncture
    0.58
     punct
    0.58
    APOLIS
    0.57
     dots
    0.57
    Punkt
    0.57
     "..\..\
    0.56
     CGPoint
    0.56
    Activations Density 4.320%

    No Known Activations