© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5988
    Prev
    Next
    INDEX
    Explanations

    variations of the word "seal", plus sporadic appearance of "Dan" and once each of "A" and "oil"

    oai_token-act-pair · gemini-2.0-flash

    seal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GEBURTSDATUM
    -1.09
    Jeografia
    -1.06
     AssemblyCulture
    -1.06
    Personensuche
    -0.99
    tvguidetime
    -0.97
    Portale
    -0.96
    исленность
    -0.93
     Réponses
    -0.92
    invokeLater
    -0.91
    awtextra
    -0.91
    POSITIVE LOGITS
    my
    0.66
    二是
    0.66
    ről
    0.65
    em
    0.59
    وزيع
    0.58
    lhes
    0.58
    lin
    0.58
    mes
    0.57
    ern
    0.57
     blanches
    0.56
    Activations Density 1.574%

    No Known Activations