© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16273
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly used in legal and political contexts

    oai_token-act-pair · gemini-2.0-flash

    business/politics/finance

    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
     solutions
    -0.90
     ideas
    -0.90
     assumptions
    -0.85
     options
    -0.81
     settings
    -0.81
     concepts
    -0.79
     principles
    -0.79
     values
    -0.79
     methods
    -0.79
     plans
    -0.78
    POSITIVE LOGITS
     OBITUARY
    0.54
    reportWebVitals
    0.50
     touristes
    0.49
     ouvriers
    0.49
    tagext
    0.47
     CURIAM
    0.47
    IContainer
    0.46
     démocr
    0.45
     navires
    0.45
     prêtres
    0.44
    Activations Density 26.202%

    No Known Activations