© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6909
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rolling out products to customers

    oai_token-act-pair · gemini-2.0-flash

    market-related terminology

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

    Commercial contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.63
     narkoba
    -0.59
     يتيمه
    -0.58
    ípios
    -0.58
    ïsme
    -0.57
     newOwner
    -0.57
    cookieParser
    -0.55
     Noyes
    -0.54
    LayoutConstraint
    -0.53
    animous
    -0.53
    POSITIVE LOGITS
     market
    0.60
     markets
    0.59
     channel
    0.51
     channels
    0.51
     ver
    0.47
     Markets
    0.47
     function
    0.47
     산
    0.47
    market
    0.46
    AsStream
    0.46
    Activations Density 1.771%

    No Known Activations