© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6720
    Prev
    Next
    INDEX
    Explanations

    numerical and mathematical notations in documents.

    oai_token-act-pair · gemini-2.0-flash

    Code and calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     error
    -1.19
     errors
    -1.06
     uncertainties
    -1.05
     uncertainty
    -1.04
    error
    -1.00
     Error
    -0.97
    Error
    -0.90
     Uncertainty
    -0.85
    Uncertainty
    -0.83
     Errors
    -0.83
    POSITIVE LOGITS
     متعلقه
    0.66
    WebServlet
    0.63
    Demografía
    0.63
    DeleteBehavior
    0.59
    CompilerServices
    0.57
    nocache
    0.57
    boxylic
    0.56
    AxisAlignment
    0.53
    ipedi
    0.52
    Viungo
    0.52
    Activations Density 2.586%

    No Known Activations