© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5022
    Prev
    Next
    INDEX
    Explanations

    a mix of millimeter indications, steering wheel mentions, and Chinese weather-related terms

    oai_token-act-pair · gemini-2.0-flash

    programming and data extraction

    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
     legendary
    -0.56
     evergreen
    -0.52
     pack
    -0.52
     innamor
    -0.51
     deluxe
    -0.49
     Scotch
    -0.49
     rimasto
    -0.49
     extensible
    -0.48
     gustos
    -0.47
     asciug
    -0.47
    POSITIVE LOGITS
    InstanceState
    0.77
     CreateTagHelper
    0.66
    TargetException
    0.62
     للاسماء
    0.59
    DotNetBar
    0.58
     hObject
    0.57
    PMailer
    0.56
    WebVitals
    0.56
    AddHtmlAttribute
    0.54
    tvguidetime
    0.53
    Activations Density 0.268%

    No Known Activations