© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15137
    Prev
    Next
    INDEX
    Explanations

    figure captions in scientific articles with image references, especially focusing on measurements, percentages and dataset names

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    Scientific figures/plots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RenderAtEndOf
    -0.96
     通販
    -0.75
     kasarigan
    -0.75
    StructEnd
    -0.75
     propOrder
    -0.68
    Дереккөздер
    -0.66
    FormTagHelper
    -0.62
     ←
    -0.62
     Infórmanos
    -0.60
     henvisninger
    -0.60
    POSITIVE LOGITS
     inches
    0.51
    RemoteException
    0.47
    vde
    0.47
    Partial
    0.46
     SafeMath
    0.46
    openzeppelin
    0.46
    coastal
    0.45
    acher
    0.45
     inch
    0.45
     Cape
    0.44
    Activations Density 2.059%

    No Known Activations