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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11513
    Prev
    Next
    INDEX
    Explanations

    code snippets including markup/script

    oai_token-act-pair · gemini-2.0-flash

    code block structures or delimiters

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

    {

    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
    AndEndTag
    -0.80
     समीक्षक
    -0.71
     AssemblyProduct
    -0.68
     ISNI
    -0.66
     שוליים
    -0.60
    apimachinery
    -0.57
    TagHelper
    -0.55
    الإنجليزية
    -0.51
    :][
    -0.51
    PropertyGroup
    -0.50
    POSITIVE LOGITS
    "){
    0.58
    CardContent
    0.56
    AndroidJUnit
    0.56
    >*/
    0.55
    "},
    0.54
    NegativeButton
    0.53
    aways
    0.52
    chromedriver
    0.52
    rinha
    0.51
    FECT
    0.50
    Activations Density 0.470%

    No Known Activations