© 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. 6656
    Prev
    Next
    INDEX
    Explanations

    phrases implying a question and answer format

    oai_token-act-pair · gemini-2.0-flash

    words with specific prefixes or unique characters

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

    requests and assistance

    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
     AssemblyCulture
    -0.88
    DockStyle
    -0.80
    IsContent
    -0.79
     autorytatywna
    -0.77
    Бахар
    -0.73
    TagMode
    -0.72
    webElementXpaths
    -0.71
    sizeCache
    -0.69
    HtmlAttribute
    -0.69
    حياته
    -0.64
    POSITIVE LOGITS
    sprogramm
    0.47
    ronesia
    0.46
    rillas
    0.45
    ATIVA
    0.44
     irons
    0.41
    szönöm
    0.39
     LEV
    0.39
    SDL
    0.39
    据
    0.39
     ity
    0.38
    Activations Density 0.492%

    No Known Activations