© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12357
    Prev
    Next
    INDEX
    Explanations

    legal terminology, court documents, and names

    oai_token-act-pair · gemini-2.0-flash

    underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     unknownFields
    -1.01
    GEBURTSDATUM
    -0.84
     beginnetje
    -0.82
     estekak
    -0.78
    SourceChecksum
    -0.78
    AutoScaleMode
    -0.76
    makeConstraints
    -0.74
     StatefulWidget
    -0.73
     AssemblyVersion
    -0.71
    __':
    -0.71
    POSITIVE LOGITS
    westen
    0.52
    camiento
    0.51
     спро
    0.50
    到底
    0.47
     inz
    0.47
    NAMESPACE
    0.47
    rager
    0.46
    porte
    0.46
     kaz
    0.46
    Mau
    0.45
    Activations Density 3.741%

    No Known Activations