© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1791
    Prev
    Next
    INDEX
    Explanations

    words and phrases about money and investment

    oai_token-act-pair · gemini-2.0-flash

    terms related to investments and financial transactions

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

    invest

    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
    Negative Logits
     AssemblyCulture
    -0.70
    الحياه
    -0.69
    قایناقلار
    -0.66
    はじめに
    -0.58
    lossians
    -0.56
    #+#
    -0.55
     puissiez
    -0.55
     tartalomajánló
    -0.55
    neté
    -0.54
    keyColumn
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.56
     Exactos
    0.56
    ьаж
    0.55
     صوتيه
    0.54
     Dostupné
    0.53
     GeoNames
    0.49
     nahilalakip
    0.49
    cshtml
    0.47
    ča
    0.46
     onFailure
    0.46
    Activations Density 3.571%

    No Known Activations