© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2152
    Prev
    Next
    INDEX
    Explanations

    names of herbs and spices, especially in the context of scientific studies

    oai_token-act-pair · gemini-2.0-flash

    spice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Horizonte
    -0.55
    TypedDataSet
    -0.55
    XmlType
    -0.50
    DebuggerNonUser
    -0.49
    gráfica
    -0.49
    ❋
    -0.49
    CLAIMER
    -0.48
     kasarigan
    -0.48
    AndroidJUnit
    -0.48
     dequeue
    -0.46
    POSITIVE LOGITS
    ngdoc
    0.75
    DockStyle
    0.56
     BorderRadius
    0.56
    rxjs
    0.54
    cauciones
    0.54
    ConstraintMaker
    0.51
    foul
    0.50
    mitsub
    0.50
    cooked
    0.50
    blurRadius
    0.49
    Activations Density 1.059%

    No Known Activations