© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11322
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and demonstrative adjectives in the context of specific places or times

    oai_token-act-pair · gemini-2.0-flash

    specific point in time

    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
     Points
    -0.55
    Points
    -0.50
    addGap
    -0.50
    ÍSTICAS
    -0.47
     points
    -0.47
     ví
    -0.45
    apar
    -0.45
    分
    -0.45
     Time
    -0.43
    points
    -0.43
    POSITIVE LOGITS
    RegistryLite
    0.93
     propOrder
    0.90
    MemoryWarning
    0.75
    StoryboardSegue
    0.69
    SceneManagement
    0.69
    TagMode
    0.68
    GEBURTSDATUM
    0.68
     AssemblyCulture
    0.66
    Portale
    0.62
    存于互联网档案馆
    0.62
    Activations Density 8.268%

    No Known Activations