Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16096
    Prev
    Next
    INDEX
    Explanations

    testamonies from figures of authority in legal settings, and other proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    Names in news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ValueStyle
    -0.62
    KommentareTeilen
    -0.61
    >{@
    -0.56
     ujednoznacz
    -0.56
    ContentAsync
    -0.55
    OGND
    -0.54
    PMailer
    -0.54
    SequentialGroup
    -0.52
     ControllerBase
    -0.52
     pageNo
    -0.50
    POSITIVE LOGITS
     الرياضيه
    0.59
    ندران
    0.59
    tanleria
    0.57
    లాలు
    0.56
    ̍t
    0.55
    Portale
    0.53
    LEncoder
    0.51
     nahilalakip
    0.51
    ridgeshire
    0.51
     Paglinawan
    0.51
    Activations Density 0.454%

    No Known Activations