© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6683
    Prev
    Next
    INDEX
    Explanations

    computer code snippets containing parameters, values, categories and data.

    oai_token-act-pair · gemini-2.0-flash

    words related to product parameters

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

    products and e-commerce

    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
    ậc
    -0.50
    blico
    -0.49
     GenerationType
    -0.49
     пора
    -0.45
    batore
    -0.45
    ंदीखरीदारी
    -0.44
     Puntos
    -0.44
    ReusableCell
    -0.44
    يميديا
    -0.43
    support
    -0.43
    POSITIVE LOGITS
     كومونز
    0.72
     ModelExpression
    0.63
    FMC
    0.58
     بيها
    0.57
    帖最后由
    0.56
    amet
    0.56
    Datuak
    0.55
     product
    0.54
     products
    0.54
     MenuView
    0.53
    Activations Density 3.155%

    No Known Activations