© 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. 5495
    Prev
    Next
    INDEX
    Explanations

    technical writing involving gasses and particles

    oai_token-act-pair · gemini-2.0-flash

    Scientific, technical texts

    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
    PerformLayout
    -0.75
     StatefulWidget
    -0.74
     للمعارف
    -0.73
    Personendaten
    -0.72
    potranspiration
    -0.68
     StatelessWidget
    -0.67
     Normdatei
    -0.66
     intptr
    -0.65
    ServletException
    -0.64
    SharedCtor
    -0.64
    POSITIVE LOGITS
     sentenza
    0.64
     sayap
    0.63
     nationaux
    0.63
     mariée
    0.62
     gouttes
    0.60
     kér
    0.58
     steder
    0.58
     enged
    0.57
     sparks
    0.57
    envolvimento
    0.56
    Activations Density 17.190%

    No Known Activations