© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12632
    Prev
    Next
    INDEX
    Explanations

    terms related to television broadcasts, particularly news programs and casts

    oai_token-act-pair · gemini-2.0-flash

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     news
    -2.28
    news
    -2.14
     News
    -2.13
    News
    -2.11
     NEWS
    -1.85
    NEWS
    -1.78
     noticias
    -1.48
     berita
    -1.39
     noticia
    -1.34
     notícia
    -1.27
    POSITIVE LOGITS
     فريبيس
    0.79
     TextAppearance
    0.66
    parsedMessage
    0.62
     ($("#
    0.61
     []:
    0.60
     mids
    0.59
    ctrica
    0.59
    ChildScrollView
    0.58
    )}</
    0.58
    ]='\
    0.58
    Activations Density 3.560%

    No Known Activations