© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16161
    Prev
    Next
    INDEX
    Explanations

    words related to academic research, particularly in the fields of physics, mathematics, and medical imaging.

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical terms

    np_max-act · gemini-2.0-flash

    scientific terms Method used: 1

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Wavelength
    -0.99
    Transcrip
    -0.86
    isometric
    -0.85
    wavelength
    -0.85
    transpiration
    -0.84
    carboxylic
    -0.84
    Fluorescence
    -0.83
    Diffuse
    -0.83
    homology
    -0.83
    Permutation
    -0.82
    POSITIVE LOGITS
    RegressionTest
    1.00
    InjectAttribute
    0.98
    complexContent
    0.97
    PyExc
    0.91
    )");
    0.85
    Personendaten
    0.84
    HasBeenSet
    0.84
    yntaxException
    0.83
    kháu
    0.83
    matchCondition
    0.82
    Activations Density 5.617%

    No Known Activations