© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12630
    Prev
    Next
    INDEX
    Explanations

    snippets of LaTeX code and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    specialized programming or technical terms

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

    scientific/mathematical texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.52
     hap
    -0.48
     Sweat
    -0.47
     initComponents
    -0.44
     Lehr
    -0.43
    aarrggbb
    -0.43
    WebElementEntity
    -0.43
     '\\;'
    -0.42
    Deserialize
    -0.42
    werb
    -0.39
    POSITIVE LOGITS
     AppCompatTheme
    0.70
     vectorielle
    0.70
    ArrowToggle
    0.66
    ContentAsync
    0.62
    ^(@)
    0.60
     houſe
    0.60
    Filmografie
    0.59
    mybatisplus
    0.59
    GEBURTS
    0.59
    documentclass
    0.58
    Activations Density 13.111%

    No Known Activations