© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    sentences describing buildings, statues, or other monuments and the dates or circumstances around their construction, destruction, or dedication.

    oai_token-act-pair · gemini-2.0-flash

    was/were/is

    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
    tonode
    -0.61
     punitive
    -0.50
     trasparente
    -0.49
    ToMany
    -0.49
     médicaux
    -0.48
    ámara
    -0.48
     occhiali
    -0.48
     vectorielles
    -0.48
    Pageable
    -0.48
     Antenna
    -0.48
    POSITIVE LOGITS
     ویکی‌پدی
    0.65
    DockStyle
    0.62
     كومونز
    0.60
    JNIEnv
    0.57
     initComponents
    0.52
    TypedDataSet
    0.52
    TouchListener
    0.52
    ttino
    0.52
    WEBPACK
    0.51
    XmlIgnore
    0.51
    Activations Density 1.693%

    No Known Activations