© 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. 5265
    Prev
    Next
    INDEX
    Explanations

    a complicated mix of mathematical equations, water-related terms, and words associated with crime and investigation.

    oai_token-act-pair · gemini-2.0-flash

    Scientific and mathematical contexts

    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
     Sol
    -2.11
    Sol
    -2.08
     sol
    -2.06
     SOL
    -2.05
    sol
    -1.96
    SOL
    -1.94
     solved
    -1.88
     solving
    -1.87
     Solve
    -1.81
     solve
    -1.80
    POSITIVE LOGITS
    Према
    0.61
    новниш
    0.60
     Comstock
    0.57
    الإنجليزية
    0.54
    dataclass
    0.53
     <<<<<<<<<<<<<<
    0.52
    はじめに
    0.51
    urro
    0.49
     néglig
    0.47
    getItemId
    0.47
    Activations Density 3.211%

    No Known Activations