© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5638
    Prev
    Next
    INDEX
    Explanations

    snippets of code in a variety of computer languages

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    quels
    -0.83
     Which
    -0.81
     which
    -0.76
     laquelle
    -0.75
     lesquels
    -0.75
    Which
    -0.74
    quelles
    -0.72
     lequel
    -0.71
     WHICH
    -0.70
     vilket
    -0.66
    POSITIVE LOGITS
     that
    2.67
    that
    1.98
     bahwa
    1.46
     dass
    1.39
     że
    1.30
    That
    1.29
     That
    1.24
     rằng
    1.21
    THAT
    1.20
     que
    1.16
    Activations Density 2.249%

    No Known Activations