© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8171
    Prev
    Next
    INDEX
    Explanations

    code snippets including references, bindings, or URLs

    oai_token-act-pair · gemini-2.0-flash

    code fragments or logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     dunque
    -0.55
    .
    -0.54
     bună
    -0.54
     consommateurs
    -0.54
    used
    -0.52
     bune
    -0.52
     professionisti
    -0.50
    _
    -0.48
     împreună
    -0.48
     käytet
    -0.48
    POSITIVE LOGITS
    NUMX
    0.92
    <bos>
    0.89
    ")){
    0.86
    ]){
    0.85
    )];
    0.83
    parsedMessage
    0.82
    //}
    0.81
    ()]
    0.79
    //{
    0.78
    ])):
    0.77
    Activations Density 1.297%

    No Known Activations