© 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. 4771
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to schooling, training, and education

    oai_token-act-pair · gemini-2.0-flash

    educational background

    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
     AssemblyProduct
    -0.50
     Publishing
    -0.50
     carlo
    -0.49
    WithIdentifier
    -0.47
    Publishing
    -0.47
     SERVER
    -0.46
    NgModule
    -0.46
    ặc
    -0.46
    ั่ว
    -0.45
     Roskov
    -0.45
    POSITIVE LOGITS
    Rhestr
    0.68
    رير
    0.60
    этому
    0.58
    
    0.58
    ddots
    0.56
    OrCreate
    0.56
     تضيفلها
    0.55
    
    0.53
    Véxase
    0.53
    contentLoaded
    0.51
    Activations Density 7.386%

    No Known Activations