© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    words related to continuing or sustaining something

    oai_token-act-pair · gemini-2.0-flash

    Technical jargon

    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
     maintenance
    -2.66
     Maintenance
    -2.52
    Maintenance
    -2.45
    maintenance
    -2.36
     maintain
    -2.28
     maintained
    -2.25
     Maintaining
    -2.23
    Maintaining
    -2.23
     maintaining
    -2.22
    maintain
    -2.16
    POSITIVE LOGITS
    protoc
    0.59
    URLException
    0.58
    pushFollow
    0.55
     désolés
    0.53
    kloped
    0.53
     CreateTagHelper
    0.52
    FileChooser
    0.50
    TintMode
    0.50
    KURZBESCHREIBUNG
    0.49
     plotly
    0.48
    Activations Density 3.146%

    No Known Activations