© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9993
    Prev
    Next
    INDEX
    Explanations

    a complex combination of database terms, java code related terms, and geopolitical figures/terms

    oai_token-act-pair · gemini-2.0-flash

    AttributeSet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     WaitForSeconds
    -0.90
     متعلقه
    -0.79
    DockStyle
    -0.78
    tagext
    -0.76
     &___
    -0.73
    FailureListener
    -0.66
    UnsafeEnabled
    -0.65
    wpi
    -0.65
    RunWith
    -0.62
     Filho
    -0.62
    POSITIVE LOGITS
    chin
    0.52
    ále
    0.50
    Pri
    0.49
    KeyPressed
    0.49
    partements
    0.47
    Chi
    0.45
    imprimir
    0.45
     Pri
    0.44
     sota
    0.44
    <bos>
    0.43
    Activations Density 14.828%

    No Known Activations