© 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. 8137
    Prev
    Next
    INDEX
    Explanations

    academic or procedural language and verbs related to research or examination

    oai_token-act-pair · gemini-2.0-flash

    scientific, academic context

    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
     Ways
    -0.87
     issue
    -0.87
     How
    -0.80
    Ways
    -0.78
     issues
    -0.77
     HOW
    -0.76
    How
    -0.74
     WAYS
    -0.73
    Issues
    -0.73
     Issue
    -0.73
    POSITIVE LOGITS
     noDo
    0.49
    blockList
    0.46
     تضيفلها
    0.45
    ▻
    0.45
    SequentialGroup
    0.43
    
    0.43
     Vikipedi
    0.43
     Wiktionnaire
    0.43
    /***/
    0.43
     ModelExpression
    0.42
    Activations Density 7.858%

    No Known Activations