© 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. 9999
    Prev
    Next
    INDEX
    Explanations

    text relating to legal and governmental processes, compliance and acts

    oai_token-act-pair · gemini-2.0-flash

    Legal and governmental topics

    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
     BoxDecoration
    -0.72
    ecake
    -0.68
    AnchorStyles
    -0.61
     StatefulWidget
    -0.60
     NSCoder
    -0.57
    weets
    -0.57
    IGraphics
    -0.57
     Spade
    -0.55
    EndContext
    -0.52
    ADUATE
    -0.52
    POSITIVE LOGITS
     colorés
    0.52
     gomma
    0.49
     Neighbourhood
    0.47
     Ucrania
    0.47
     africains
    0.47
     pétrole
    0.46
     RTI
    0.46
     Counseling
    0.45
     Community
    0.45
     pauvres
    0.44
    Activations Density 41.619%

    No Known Activations