© 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. 5378
    Prev
    Next
    INDEX
    Explanations

    form field related terms and data handling commitments

    oai_token-act-pair · gemini-2.0-flash

    words indicating guarantees or commitments

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

    segments of documents

    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
     purpoſe
    -0.96
     Reſ
    -0.96
     itſelf
    -0.89
     pleaſure
    -0.88
     Jefus
    -0.86
     myſelf
    -0.84
     leſs
    -0.84
     ſever
    -0.82
     uſe
    -0.82
     Italijanski
    -0.80
    POSITIVE LOGITS
     down
    0.56
     B
    0.52
     common
    0.48
     final
    0.47
     must
    0.46
    neri
    0.44
     T
    0.43
     com
    0.42
     come
    0.42
     She
    0.42
    Activations Density 1.147%

    No Known Activations