© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5973
    Prev
    Next
    INDEX
    Explanations

    a mix of elements including genetic mutation nomenclature, mathematical notation, chemical formulas, and travel-related terms, possibly related to scientific or technical documents about travel

    oai_token-act-pair · gemini-2.0-flash

    Code/Math

    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
     للاسماء
    -0.54
     مرئيه
    -0.51
     سكانية
    -0.50
     EconPapers
    -0.49
    ########.
    -0.48
     saites
    -0.45
    цездатний
    -0.45
    Personensuche
    -0.44
     esternos
    -0.43
     @"/
    -0.43
    POSITIVE LOGITS
     getById
    0.87
    yorsunuz
    0.77
    EMOS
    0.75
    ESSMENT
    0.74
    ]--;
    0.71
    }}]{
    0.71
     ་་
    0.70
    ERÍA
    0.70
    leſs
    0.70
    地说道
    0.69
    Activations Density 10.553%

    No Known Activations