© 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. 11978
    Prev
    Next
    INDEX
    Explanations

    words that might be present in scientific documents, including chemical names, Korean names, and names of attacks

    oai_token-act-pair · gemini-2.0-flash

    on

    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
    Personendaten
    -0.86
     typelib
    -0.66
    ParallelGroup
    -0.65
    CodedInputStream
    -0.61
    :✨
    -0.56
     насељу
    -0.56
    homonymie
    -0.55
    lera
    -0.55
    ANNON
    -0.54
    AutoScaleMode
    -0.54
    POSITIVE LOGITS
     récents
    0.53
     InputDecoration
    0.51
    makeText
    0.48
     mø
    0.47
     насеље
    0.46
     genauer
    0.46
     mourut
    0.45
     partenaire
    0.45
    atguigu
    0.44
     poveznice
    0.43
    Activations Density 13.261%

    No Known Activations