© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    words related to Turkey, especially place names, earthquakes and cuisine

    oai_token-act-pair · gemini-2.0-flash

    multiple news sources

    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
    tagHelperRunner
    -0.75
    ograma
    -0.67
    )|^{
    -0.64
    AddHtmlAttribute
    -0.63
     الرخصة
    -0.62
    uitable
    -0.62
    målet
    -0.61
    enumi
    -0.60
    )]);
    -0.60
    ,:]
    -0.59
    POSITIVE LOGITS
     Himo
    0.41
     anomalous
    0.39
     drake
    0.39
    ığınız
    0.38
    سطس
    0.37
    ığında
    0.37
    ığını
    0.36
     plaine
    0.35
    "?>
    0.35
     فريبيس
    0.35
    Activations Density 0.244%

    No Known Activations