© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    scientific or medical research results, including numerical results, study design information and citations

    oai_token-act-pair · gemini-2.0-flash

    Medical studies

    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
     ProtoMessage
    -1.03
     Савезне
    -1.02
    <bos>
    -1.02
     Paglinawan
    -0.99
     Roskov
    -0.96
     Мексичка
    -0.95
    CppCodeGen
    -0.94
     resourceCulture
    -0.90
     AssemblyCulture
    -0.83
     MainAxisSize
    -0.83
    POSITIVE LOGITS
    taza
    0.52
     step
    0.49
     end
    0.47
    0.47
     subsequent
    0.46
    accia
    0.46
    beak
    0.46
     colo
    0.45
     Het
    0.45
    appen
    0.45
    Activations Density 1.139%

    No Known Activations