© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    words relating to sports, especially player trades and rumors

    oai_token-act-pair · gemini-2.0-flash

    rumor

    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
    LookAnd
    -1.03
    awtextra
    -0.98
    RegressionTest
    -0.94
     nahilalakip
    -0.90
    oredCriteria
    -0.85
     &___
    -0.82
     nakalista
    -0.80
    rungsseite
    -0.79
    parsedMessage
    -0.78
    findpost
    -0.78
    POSITIVE LOGITS
    allin
    0.39
    VERIFY
    0.39
     aéri
    0.39
     Alcalde
    0.38
     Сайт
    0.38
     التجار
    0.38
     Produit
    0.37
     voler
    0.36
    ibin
    0.36
    veri
    0.36
    Activations Density 18.682%

    No Known Activations