© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    words and phrases that typically appear in technical descriptions of inventions, patents, and processes.

    oai_token-act-pair · gemini-2.0-flash

    industrial processes

    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
     متعلقه
    -0.68
     initComponents
    -0.59
     Infórmanos
    -0.56
     formation
    -0.56
    řev
    -0.55
    transQ
    -0.54
     surla
    -0.53
     restauration
    -0.50
     مشين
    -0.50
     lector
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.65
    mybatisplus
    0.63
    tonode
    0.60
    getDoctrine
    0.60
    twimg
    0.57
    AutoField
    0.56
     Epi
    0.54
     icing
    0.53
    initializeApp
    0.53
    endurch
    0.53
    Activations Density 7.737%

    No Known Activations