© 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. 6813
    Prev
    Next
    INDEX
    Explanations

    legal and mathematical text

    oai_token-act-pair · gemini-2.0-flash

    HTML or XML elements

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

    Incomplete sentences

    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
     itſelf
    -1.46
     Shakspeare
    -1.39
     myſelf
    -1.26
     Jefus
    -1.25
     Cæsar
    -1.23
     Monfieur
    -1.22
     Chriftian
    -1.22
     Houſe
    -1.21
     Efq
    -1.20
     Diſ
    -1.16
    POSITIVE LOGITS
    <blockquote>
    0.80
    </strong>
    0.78
     Z
    0.73
     to
    0.71
     a
    0.71
     man
    0.71
     li
    0.70
    ‍
    0.69
     
    0.69
     an
    0.68
    Activations Density 0.859%

    No Known Activations