© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13948
    Prev
    Next
    INDEX
    Explanations

    legal and government terms, particularly related to due process and amendments.

    oai_token-act-pair · gemini-2.0-flash

    words related to due process and legal terminology

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

    constitutional rights

    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
    
    -0.85
    GOTREF
    -0.83
    mybatisplus
    -0.77
     faſt
    -0.66
     архивлан
    -0.66
    /*
    -0.66
    sizeCache
    -0.65
    AsUp
    -0.64
    forChild
    -0.64
    Personensuche
    -0.64
    POSITIVE LOGITS
     ‘
    0.60
     '
    0.57
     due
    0.57
     New
    0.55
     di
    0.55
     Due
    0.53
    AndEndTag
    0.52
     “
    0.51
    isure
    0.50
     saites
    0.50
    Activations Density 5.969%

    No Known Activations