© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9007
    Prev
    Next
    INDEX
    Explanations

    tokens related to events happening

    oai_token-act-pair · gemini-2.0-flash

    regular occurrences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    -0.67
     Signalez
    -0.63
    __":
    -0.62
    interopRequire
    -0.58
    WriteAttribute
    -0.57
     arşivlendi
    -0.57
    Hentet
    -0.56
    ByVersion
    -0.55
    __':
    -0.55
     transférez
    -0.54
    POSITIVE LOGITS
     daily
    1.25
     everyday
    1.23
     regularly
    1.16
     Everyday
    1.15
    everyday
    1.14
    Everyday
    1.09
    daily
    1.06
     constantly
    1.01
    Daily
    0.97
     routinely
    0.94
    Activations Density 1.768%

    No Known Activations