© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4424
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    oai_token-act-pair · gemini-2.0-flash

    say coding symbols

    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
    ."]
    -1.06
    ."],
    -1.01
    "]];
    -0.94
    ."</
    -0.93
    .');
    -0.92
    "](
    -0.90
    ."));
    -0.90
    "]]
    -0.90
    .");
    -0.89
    .-(
    -0.87
    POSITIVE LOGITS
    ,
    0.98
    )
    0.77
     ,
    0.71
    ){
    0.63
     )
    0.60
    ,,
    0.54
    1
    0.54
     /*
    0.52
    <bos>
    0.51
     ||
    0.48
    Activations Density 3.291%

    No Known Activations