© 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. 14665
    Prev
    Next
    INDEX
    Explanations

    code snippets related to XML and JSON serialization and deserialization

    oai_token-act-pair · gemini-2.0-flash

    String

    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
    立て
    -0.50
    Geplaatst
    -0.49
    itemBuilder
    -0.48
     cuchar
    -0.47
     gång
    -0.47
     levier
    -0.46
     letto
    -0.45
     lentement
    -0.45
     quidem
    -0.44
    త్ర
    -0.44
    POSITIVE LOGITS
     String
    1.48
    String
    1.47
     Strings
    0.81
     strings
    0.69
    exitRule
    0.67
    ItemBackground
    0.66
    makeText
    0.60
    Strings
    0.60
    orace
    0.59
     STRING
    0.58
    Activations Density 1.756%

    No Known Activations