© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11852
    Prev
    Next
    INDEX
    Explanations

    articles referencing the country of Swaziland, its politics, and/or poverty

    oai_token-act-pair · gemini-2.0-flash

    Swaziland social/political issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.96
     pinulongan
    -0.54
     Narrow
    -0.53
    Rptr
    -0.51
     narrow
    -0.49
    ména
    -0.47
    AndroidJUnit
    -0.47
    Charset
    -0.46
    charset
    -0.45
     utafitiHapana
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.65
    RenderAtEndOf
    0.59
    makeConstraints
    0.57
    IBarButtonItem
    0.56
    ConstraintMaker
    0.54
    "}}
    0.54
    出版年
    0.53
    iteiten
    0.53
    TagHelper
    0.52
    RunAsync
    0.52
    Activations Density 1.401%

    No Known Activations