© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15597
    Prev
    Next
    INDEX
    Explanations

    scientific or technical writing describing a setup including water, pumps, tubes, and containers of a particular volume.

    oai_token-act-pair · gemini-2.0-flash

    filtered substances or processes

    np_token-act-pair-logits · gpt-4o-mini

    Scientific studies involving animals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.84
    RenderAtEndOf
    -0.79
    ValueStyle
    -0.78
    ThroughAttribute
    -0.77
     تضيفلها
    -0.76
    webElementXpaths
    -0.75
    IBarButtonItem
    -0.74
    principalColumn
    -0.73
     ModelExpression
    -0.71
    ResumeLayout
    -0.71
    POSITIVE LOGITS
     filter
    0.56
     ad
    0.52
     air
    0.50
     R
    0.48
    filter
    0.47
    abor
    0.46
     par
    0.45
     Super
    0.45
    ilsen
    0.44
     parti
    0.43
    Activations Density 1.780%

    No Known Activations