© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6069
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings, including immigration and criminal justice

    oai_token-act-pair · gemini-2.0-flash

    terms related to immigration and legal status

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

    Immigration

    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
     Normdatei
    -0.59
    saraba
    -0.59
     aDecoder
    -0.57
    hyrchwyd
    -0.53
    Denomin
    -0.52
    Externé
    -0.52
    naut
    -0.50
     الدولى
    -0.49
     Bucure
    -0.49
     OnInit
    -0.47
    POSITIVE LOGITS
    principalColumn
    0.67
     Home
    0.63
     Calais
    0.60
     Dernière
    0.60
    Home
    0.57
     home
    0.56
     Migration
    0.53
     migration
    0.53
     Border
    0.52
     detention
    0.52
    Activations Density 2.474%

    No Known Activations