© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5358
    Prev
    Next
    INDEX
    Explanations

    scientific experimental methodology using electron microscopes

    oai_token-act-pair · gemini-2.0-flash

    identifiers and technical terms in scientific analysis

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

    Electron microscopes and lithography

    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
    viste
    -0.48
    closePath
    -0.47
    anat
    -0.47
     Pula
    -0.45
    ternut
    -0.44
    firm
    -0.42
    dels
    -0.41
    ignty
    -0.40
     firm
    -0.40
    ahi
    -0.40
    POSITIVE LOGITS
    featureID
    0.86
    Trama
    0.73
    #+#
    0.69
     &___
    0.68
    AccessorTable
    0.68
    FunctionFlags
    0.68
    RegressionTest
    0.68
    Lähteet
    0.66
    URLException
    0.63
     <",
    0.62
    Activations Density 2.255%

    No Known Activations