© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5387
    Prev
    Next
    INDEX
    Explanations

    angle brackets that are typically part of include statements in C++ code

    oai_token-act-pair · gemini-2.0-flash

    Less than sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     welcome
    -0.94
     WELCOME
    -0.81
     Welcome
    -0.79
    welcome
    -0.77
    Welcome
    -0.74
    WELCOME
    -0.74
     welcomed
    -0.72
    elcome
    -0.69
     bienvenue
    -0.63
     welcomes
    -0.61
    POSITIVE LOGITS
     Thiel
    0.53
     GetEnumerator
    0.53
    Välislingid
    0.50
    iostream
    0.49
    Спољашње
    0.49
    assert
    0.49
    DotNetBar
    0.47
    Sklici
    0.47
    ++)
    0.47
    出版年
    0.47
    Activations Density 0.320%

    No Known Activations