© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14236
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, places, companies, and fictional characters

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns/named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     NSCoder
    -0.82
     незавершена
    -0.75
    UnusedPrivate
    -0.68
    fromnode
    -0.67
    keyColumn
    -0.65
     nahilalakip
    -0.65
    WireFormatLite
    -0.64
    CodeAttribute
    -0.63
     acrylique
    -0.62
     silnika
    -0.62
    POSITIVE LOGITS
    <bos>
    0.56
    totalPage
    0.48
    mbalikan
    0.47
     middel
    0.47
     gynhyrchwyd
    0.47
     de
    0.45
    lapsingToolbar
    0.45
    imental
    0.45
     Фе
    0.44
     Fer
    0.44
    Activations Density 4.586%

    No Known Activations