© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13329
    Prev
    Next
    INDEX
    Explanations

    a variety of common words, especially when used in short sentences or lists, sometimes in the context of web design and also in the context of football (soccer) analysis.

    oai_token-act-pair · gemini-2.0-flash

    coding/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    proper
    -3.00
     proper
    -2.98
     Proper
    -2.84
    Proper
    -2.72
     PROPER
    -2.44
    properly
    -2.20
     properly
    -2.20
     Properly
    -1.95
     improper
    -1.41
     richtigen
    -1.20
    POSITIVE LOGITS
    InjectAttribute
    0.68
    WireFormatLite
    0.59
    WEBPACK
    0.58
     المعيارى
    0.57
    XMLSchema
    0.56
    ForValue
    0.56
    ImageIO
    0.54
    deelte
    0.54
     onCancelled
    0.51
    kmäler
    0.50
    Activations Density 5.797%

    No Known Activations