© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15409
    Prev
    Next
    INDEX
    Explanations

    words about a person or object that's powerful, magical, and/or has high status.

    oai_token-act-pair · gemini-2.0-flash

    big

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     MainAxisSize
    -0.59
    main
    -0.54
     gegangen
    -0.53
    mains
    -0.52
    QMetaType
    -0.51
     chiama
    -0.50
     ligiloj
    -0.48
     esegu
    -0.48
     وتسجيلات
    -0.48
     rispet
    -0.47
    POSITIVE LOGITS
     ujednoznacz
    0.59
    Попис
    0.58
    urlencoded
    0.55
    WriteBarrier
    0.55
    typeorm
    0.54
    lossians
    0.52
    Ethylbenzene
    0.52
     knowledge
    0.51
    ButterKnife
    0.50
    StateException
    0.50
    Activations Density 0.440%

    No Known Activations