© 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. 12346
    Prev
    Next
    INDEX
    Explanations

    terms related to the broadcasting of news and other television content, including cable, networks, and channels

    oai_token-act-pair · gemini-2.0-flash

    channel

    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
     channel
    -2.63
     Channel
    -2.34
    channel
    -2.34
     CHANNEL
    -2.28
     channels
    -2.25
    Channel
    -2.22
     Channels
    -2.06
    channels
    -1.96
    CHANNEL
    -1.90
    Channels
    -1.82
    POSITIVE LOGITS
     चीज़ों
    0.68
    emark
    0.62
     المعيارى
    0.61
    POLE
    0.59
     conci
    0.59
    ніципа
    0.59
    OLPH
    0.59
     مواليد
    0.57
    ilst
    0.57
    Ferdin
    0.56
    Activations Density 13.439%

    No Known Activations