© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14723
    Prev
    Next
    INDEX
    Explanations

    mentions of launches or missions related to celestial bodies

    oai_token-act-pair · gemini-2.0-flash

    rockets and space

    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
     تضيفلها
    -0.81
    الحياه
    -0.73
    UnitTesting
    -0.66
     الرياضيه
    -0.64
    newswire
    -0.63
    Gambas
    -0.61
    DockStyle
    -0.60
    ImageContext
    -0.60
    StructEnd
    -0.59
     AssemblyCulture
    -0.58
    POSITIVE LOGITS
    WireFormat
    0.48
    xaml
    0.42
     senior
    0.42
    Ι
    0.41
     trung
    0.40
     dica
    0.40
    清明
    0.40
     Delta
    0.40
    queros
    0.40
    StringBuffer
    0.40
    Activations Density 1.316%

    No Known Activations