© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15752
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to property ownership and legal documents

    oai_token-act-pair · gemini-2.0-flash

    operator/operation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ownership
    -1.12
     Ownership
    -1.08
     owner
    -1.03
    owner
    -0.99
     Owner
    -0.97
    Ownership
    -0.94
    ownership
    -0.93
    owners
    -0.92
     owned
    -0.92
     owners
    -0.91
    POSITIVE LOGITS
     operator
    0.72
     operators
    0.72
    operator
    0.67
     Operators
    0.66
    Operator
    0.66
     operated
    0.65
    operators
    0.64
     Operator
    0.62
     Operate
    0.60
     operate
    0.60
    Activations Density 0.518%

    No Known Activations