© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1673
    Prev
    Next
    INDEX
    Explanations

    words and phrases from technical documents about sales and products

    oai_token-act-pair · gemini-2.0-flash

    say "sold" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     selling
    -2.39
     sales
    -2.30
     Selling
    -2.27
     sell
    -2.27
     Sales
    -2.17
    Selling
    -2.17
     sells
    -2.16
     sale
    -2.14
    sales
    -2.13
    Sales
    -2.11
    POSITIVE LOGITS
    old
    0.42
    endsection
    0.36
    Enrique
    0.35
    hdessä
    0.34
    HttpClientModule
    0.33
    epam
    0.32
    θεν
    0.31
    ale
    0.31
    Filmografie
    0.31
    гова
    0.31
    Activations Density 1.224%

    No Known Activations