© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9876
    Prev
    Next
    INDEX
    Explanations

    references to changes across time periods

    oai_token-act-pair · gemini-2.0-flash

    year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyProduct
    -0.66
    rungsseite
    -0.65
    MigrationBuilder
    -0.64
    ContentAsync
    -0.63
     nonUne
    -0.62
    Diwedd
    -0.60
    Kaynakça
    -0.59
    invokeLater
    -0.57
    broek
    -0.55
    !*\
    -0.53
    POSITIVE LOGITS
     over
    0.49
    ,!
    0.48
     ligiloj
    0.46
    țiunea
    0.45
     engraçadas
    0.45
    over
    0.45
    heureusement
    0.44
     JAXBElement
    0.44
    Lugares
    0.44
    rawdę
    0.43
    Activations Density 0.724%

    No Known Activations