© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12596
    Prev
    Next
    INDEX
    Explanations

    references to the current and upcoming time frame

    oai_token-act-pair · gemini-2.0-flash

    each/this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    )");
    -0.71
    InitVars
    -0.69
     فريبيس
    -0.68
    ")));
    -0.68
    .")
    -0.67
    )];
    -0.66
    '));
    -0.66
    '){
    -0.65
     NACIONAL
    -0.65
     tslint
    -0.65
    POSITIVE LOGITS
     bien
    0.48
     (
    0.48
    eleste
    0.47
    reportWebVitals
    0.47
    haupt
    0.46
     combinar
    0.46
    ását
    0.45
    happ
    0.43
    Alike
    0.43
    ClientSize
    0.43
    Activations Density 1.284%

    No Known Activations