© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10498
    Prev
    Next
    INDEX
    Explanations

    scientific parameters, maps, results, and discussions around those results

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming and technical terms

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

    results

    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
     XCTest
    -0.77
    Tracce
    -0.64
    NgModule
    -0.63
    NameInMap
    -0.59
     esboço
    -0.57
    multer
    -0.56
     Odys
    -0.56
     <=",
    -0.55
    WebVitals
    -0.55
     Brum
    -0.54
    POSITIVE LOGITS
     ApiException
    0.59
     StatelessWidget
    0.48
    Географи
    0.47
     sagesse
    0.45
    حياته
    0.44
     from
    0.43
     uovo
    0.43
     taget
    0.42
    atrician
    0.41
     chrétienne
    0.41
    Activations Density 8.028%

    No Known Activations