© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11308
    Prev
    Next
    INDEX
    Explanations

    code snippets related to checksums, data structures, or other networking related terminology

    oai_token-act-pair · gemini-2.0-flash

    sum

    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
    :✨
    -0.87
     كومونز
    -0.77
    #+#
    -0.76
    errHandler
    -0.75
     مشين
    -0.74
    Tembelea
    -0.74
    expandindo
    -0.73
     avoient
    -0.70
     étoient
    -0.70
     للمعارف
    -0.70
    POSITIVE LOGITS
     com
    0.48
     generated
    0.48
     Key
    0.47
     nonce
    0.47
     w
    0.47
     no
    0.47
     secret
    0.46
     key
    0.46
    ↵
    0.45
     const
    0.44
    Activations Density 2.815%

    No Known Activations