© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11143
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and recommendations

    oai_token-act-pair · gemini-2.0-flash

    forum/discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Duplicate
    -0.66
     duplicate
    -0.61
     replicate
    -0.52
    exactly
    -0.52
     duplicated
    -0.50
    <bos>
    -0.50
    mapbox
    -0.50
     triplicate
    -0.49
     мәкал
    -0.49
    Exactly
    -0.49
    POSITIVE LOGITS
    ViewImports
    0.80
     surla
    0.60
     كومونز
    0.60
    InjectAttribute
    0.58
    BeginContext
    0.56
    JvmStatic
    0.54
    لينا
    0.52
    apimachinery
    0.51
     trataba
    0.49
    IVEREF
    0.48
    Activations Density 3.154%

    No Known Activations