© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5816
    Prev
    Next
    INDEX
    Explanations

    mentions of gossip, rumors, or general news.

    oai_token-act-pair · gemini-2.0-flash

    Spreading information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TagMode
    -0.58
     linkovi
    -0.54
     Pequ
    -0.52
     statu
    -0.50
     Coolidge
    -0.47
    딩
    -0.45
     Betracht
    -0.45
     Interference
    -0.44
    predictor
    -0.44
    oluene
    -0.43
    POSITIVE LOGITS
     circulating
    1.32
     circulated
    1.23
     circulate
    1.19
     spread
    1.18
     circulation
    1.15
     spreads
    1.10
    spread
    1.06
     circ
    1.06
     spreading
    1.04
    Circ
    1.00
    Activations Density 1.487%

    No Known Activations