© 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. 3891
    Prev
    Next
    INDEX
    Explanations

    scientific text discussing a study including citations to other studies

    oai_token-act-pair · gemini-2.0-flash

    inequalities

    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
     فريبيس
    -0.79
    MemoryWarning
    -0.78
     disponibilités
    -0.72
    CodeAttribute
    -0.71
    getDoctrine
    -0.68
    complexContent
    -0.67
    JspWriter
    -0.66
    :+:
    -0.65
    __*/
    -0.65
     كومونز
    -0.65
    POSITIVE LOGITS
    presto
    0.41
     strict
    0.39
     aval
    0.38
    TabbedPane
    0.38
    QtWidgets
    0.38
     reverse
    0.37
    corer
    0.36
     titul
    0.36
     ويكيپيديا
    0.36
     histoire
    0.36
    Activations Density 5.789%

    No Known Activations