© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time duration or span

    oai_token-act-pair · gemini-2.0-flash

    numerical values or references to time periods

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

    for

    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
     للمعارف
    -0.80
    StoreMessageInfo
    -0.75
     fieldNum
    -0.59
    webElementXpaths
    -0.58
    قایناقلار
    -0.57
    :][
    -0.56
    WriteTagHelper
    -0.56
    Kjelder
    -0.55
    CardContent
    -0.53
    writeFieldEnd
    -0.50
    POSITIVE LOGITS
    TagHelper
    0.67
     nine
    0.66
     six
    0.64
     seven
    0.61
     CreateTagHelper
    0.61
     three
    0.60
    VersionUID
    0.59
    cshtml
    0.59
     five
    0.59
     several
    0.58
    Activations Density 3.145%

    No Known Activations