© 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. 3609
    Prev
    Next
    INDEX
    Explanations

    language related to industrial manufacturing processes and factory equipment.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    RegressionTest
    -0.77
    WebServlet
    -0.64
    PerformLayout
    -0.63
     externi
    -0.61
    crites
    -0.60
    writeFieldEnd
    -0.57
    tagHelperRunner
    -0.56
    InstanceState
    -0.51
    átku
    -0.50
    nodoc
    -0.50
    POSITIVE LOGITS
    medriver
    0.62
     générations
    0.56
     vectorielle
    0.54
    MENAFN
    0.53
     métallique
    0.53
    WebDriver
    0.52
     fallu
    0.49
     pédagogique
    0.49
     وتسجيلات
    0.49
     logistique
    0.49
    Activations Density 10.732%

    No Known Activations