© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15760
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and sentences related to news broadcasting and television

    oai_token-act-pair · gemini-2.0-flash

    breaking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.81
    News
    -0.79
    news
    -0.74
     news
    -0.73
    NEWS
    -0.69
     NEWS
    -0.66
    complexType
    -0.65
    noticia
    -0.64
    STORY
    -0.64
     noticia
    -0.61
    POSITIVE LOGITS
     breaking
    1.61
    breaking
    1.40
     Breaking
    1.38
    Breaking
    1.36
     broke
    1.34
     break
    1.26
    break
    1.24
     BREAKING
    1.22
     Break
    1.16
     breaks
    1.15
    Activations Density 1.927%

    No Known Activations