© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13523
    Prev
    Next
    INDEX
    Explanations

    terms specific to legal proceedings and laws

    oai_token-act-pair · gemini-2.0-flash

    legal power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    VIAF
    -0.79
     AssemblyVersion
    -0.56
    naux
    -0.54
    Osob
    -0.52
    rouw
    -0.50
     aDecoder
    -0.49
     comp
    -0.49
     gấp
    -0.48
     AssemblyProduct
    -0.48
    zahlen
    -0.48
    POSITIVE LOGITS
     power
    0.70
    Power
    0.62
     purpoſe
    0.59
     obstante
    0.57
     obligation
    0.57
     Power
    0.57
     femininas
    0.57
    power
    0.57
     potest
    0.56
     fiducia
    0.56
    Activations Density 10.935%

    No Known Activations