© 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. 7196
    Prev
    Next
    INDEX
    Explanations

    names of scientists and research grant programs

    oai_token-act-pair · gemini-2.0-flash

    French locations

    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
    Jeografia
    -0.56
    tagHelperRunner
    -0.52
    ArrowToggle
    -0.52
    __':
    -0.50
     mergeFrom
    -0.48
    indépendance
    -0.47
    __":
    -0.46
     propOrder
    -0.44
     RVA
    -0.44
    InjectAttribute
    -0.44
    POSITIVE LOGITS
     Loire
    0.52
    Pré
    0.52
    dieu
    0.50
     Hervé
    0.50
     Cheval
    0.50
     Pré
    0.49
     Blaise
    0.49
     Amiens
    0.48
     René
    0.48
     Nantes
    0.48
    Activations Density 29.340%

    No Known Activations