© 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. 13363
    Prev
    Next
    INDEX
    Explanations

    sentence endings, punctuation, and various discourse markers

    oai_token-act-pair · gemini-2.0-flash

    period/question mark

    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
     pinulongan
    -0.77
     يتيمه
    -0.65
     corporate
    -0.63
     marketing
    -0.62
     "..\..\
    -0.62
     infrastructure
    -0.61
     operations
    -0.60
     management
    -0.60
     integration
    -0.60
    UserScript
    -0.60
    POSITIVE LOGITS
    >(&
    0.50
     تضيفلها
    0.46
    micamente
    0.45
    Viki
    0.45
     suena
    0.42
     poem
    0.42
     dragged
    0.42
    searched
    0.41
    Begriffsklä
    0.41
    thrown
    0.40
    Activations Density 4.804%

    No Known Activations