© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1842
    Prev
    Next
    INDEX
    Explanations

    words related to cooking ingredients and recipes

    oai_token-act-pair · gemini-2.0-flash

    Cooking ingredients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    set
    -0.52
     set
    -0.45
    andri
    -0.42
     آور
    -0.42
    andır
    -0.41
    liz
    -0.41
    goto
    -0.41
     ci
    -0.41
    Mutable
    -0.41
    <eos>
    -0.40
    POSITIVE LOGITS
    JspWriter
    0.86
     חיצוניים
    0.83
    Tikang
    0.81
    AddTagHelper
    0.78
    ंदीखरीदारी
    0.77
     виправивши
    0.76
    NOPQRST
    0.76
    InputBorder
    0.75
     BoxDecoration
    0.75
    脚注の使い方
    0.73
    Activations Density 1.906%

    No Known Activations