© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2073
    Prev
    Next
    INDEX
    Explanations

    the text of a historical document and the context around it

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming keywords

    np_token-act-pair-logits · gpt-4o-mini
    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
     Quis
    -0.56
    ientí
    -0.55
     Chilean
    -0.54
     Sofía
    -0.54
     Sdn
    -0.54
    ^(@)
    -0.51
     kysy
    -0.51
     moro
    -0.50
    Alsace
    -0.50
    Ɓ
    -0.50
    POSITIVE LOGITS
     AssemblyProduct
    0.73
    Hentet
    0.69
    principalTable
    0.64
    HasForeignKey
    0.61
    IsContent
    0.59
     وتسجيلات
    0.59
    SuppressMessage
    0.59
    XmlAccessType
    0.56
    adpleegd
    0.52
    __*/
    0.52
    Activations Density 1.966%

    No Known Activations