© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13438
    Prev
    Next
    INDEX
    Explanations

    code syntax like variable assignments, conditional statements, and possibly certain keywords, especially related to configuration or default values.

    oai_token-act-pair · gemini-2.0-flash

    Code and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Default
    -2.06
    Default
    -2.02
    default
    -1.96
     default
    -1.91
     typical
    -1.87
    Typical
    -1.81
     Typical
    -1.80
    typical
    -1.72
    Usual
    -1.71
     Usual
    -1.70
    POSITIVE LOGITS
    invokeLater
    0.52
    endwhile
    0.52
    IConfiguration
    0.51
    featureID
    0.51
    niająca
    0.50
    OfMonth
    0.49
     مشار
    0.47
    queryInterface
    0.47
    CodedInputStream
    0.47
    ItemGroup
    0.46
    Activations Density 1.809%

    No Known Activations