© 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. 15636
    Prev
    Next
    INDEX
    Explanations

    references to locations in Nigeria and political/economic concepts

    oai_token-act-pair · gemini-2.0-flash

    Nigeria

    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
    <bos>
    -0.78
    المناصب
    -0.70
     تانيه
    -0.63
    sizeCache
    -0.62
     EconPapers
    -0.61
    kháu
    -0.57
    oa̍t
    -0.57
    //
    -0.56
     ddelweddau
    -0.56
    Geplaatst
    -0.55
    POSITIVE LOGITS
    ↵↵
    0.66
    {
    0.57
    ↵
    0.54
     "..\..\
    0.50
    .
    0.50
     dicendo
    0.48
    setVerticalGroup
    0.47
     "
    0.45
    一名
    0.45
    ophone
    0.45
    Activations Density 0.837%

    No Known Activations