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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3140
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with fake news and media literacy

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Meksiku
    -0.56
    webElementXpaths
    -0.53
     Pate
    -0.47
     diary
    -0.43
    Named
    -0.43
     shank
    -0.42
     bí
    -0.42
     Molière
    -0.42
     bible
    -0.42
    orice
    -0.42
    POSITIVE LOGITS
    gonic
    0.72
    parsedMessage
    0.68
    angliski
    0.62
     GetEnumerator
    0.62
    angulaire
    0.59
    PositiveButton
    0.58
    SourceChecksum
    0.56
    skechers
    0.55
    IBarButtonItem
    0.54
    MENAFN
    0.54
    Activations Density 0.638%

    No Known Activations