© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6669
    Prev
    Next
    INDEX
    Explanations

    a cluster of things. This neuron seems to find legal documents, or references to legal situations

    oai_token-act-pair · gemini-2.0-flash

    terms related to legal documentation and permits

    np_token-act-pair-logits · gpt-4o-mini

    documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    indd
    -0.55
    stdafx
    -0.47
     received
    -0.45
    PROLOG
    -0.45
     Aussicht
    -0.44
    receive
    -0.43
    ThroughAttribute
    -0.43
     Pakai
    -0.43
     receive
    -0.42
     receipt
    -0.41
    POSITIVE LOGITS
     GenerationType
    0.76
    GroupLayout
    0.59
    orp
    0.59
    dersfield
    0.59
    ArgsConstructor
    0.59
    APOLIS
    0.57
    racuse
    0.56
    stateProvider
    0.56
    exitRule
    0.56
    IsMutable
    0.55
    Activations Density 1.769%

    No Known Activations