© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15650
    Prev
    Next
    INDEX
    Explanations

    text about a soccer player named Morris, including his injuries, club affiliations, and contract negotiations.

    oai_token-act-pair · gemini-2.0-flash

    player signings

    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
    RunAsync
    -0.50
    راء
    -0.49
    RegistryLite
    -0.48
     Aquila
    -0.48
     Cap
    -0.47
     duplicate
    -0.47
    Quota
    -0.46
    copyOf
    -0.45
     EOS
    -0.45
     CAP
    -0.44
    POSITIVE LOGITS
     الحره
    0.87
     nahilalakip
    0.84
    AsUp
    0.69
    Diweddarwch
    0.59
    råd
    0.57
    XmlType
    0.56
    例文帳に追加
    0.56
     iconTwitter
    0.54
    ]--;
    0.53
    ConverterFactory
    0.53
    Activations Density 0.903%

    No Known Activations