© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    words related to the process of collecting data for scientific research

    oai_token-act-pair · gemini-2.0-flash

    gather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    djangoproject
    -0.66
     onOptions
    -0.65
    WarningLevel
    -0.63
    المشاركات
    -0.54
     actionTypes
    -0.54
     surla
    -0.52
     Bourgoin
    -0.52
     trajets
    -0.51
    CascadeType
    -0.51
    expandindo
    -0.49
    POSITIVE LOGITS
     виправивши
    0.62
     provided
    0.60
    ')):
    0.59
     Dostupné
    0.59
     provide
    0.59
    Providing
    0.58
    Supplies
    0.57
     PROVID
    0.57
     Providing
    0.56
     information
    0.55
    Activations Density 4.970%

    No Known Activations