© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14450
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    ordinal numbers

    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
     iprot
    -0.52
     ddelweddau
    -0.50
    SpringBootTest
    -0.49
    urant
    -0.49
     blanches
    -0.48
    ContentAlignment
    -0.48
    icitis
    -0.48
    uitable
    -0.47
     AssemblyTitle
    -0.45
     समीक्षक
    -0.45
    POSITIVE LOGITS
    Бахар
    0.65
    <bos>
    0.63
     Express
    0.60
    EXPRESS
    0.59
     resourceCulture
    0.57
    express
    0.57
    Express
    0.57
    IRQn
    0.57
     EXPRESS
    0.56
    haustible
    0.53
    Activations Density 1.899%

    No Known Activations