© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11033
    Prev
    Next
    INDEX
    Explanations

    text from legal documents regarding citizenship, immigration, and children

    oai_token-act-pair · gemini-2.0-flash

    minors

    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
     مشين
    -0.62
    
    -0.58
     engineered
    -0.58
    Архівовано
    -0.56
    Enllaces
    -0.52
    engineered
    -0.50
    publicain
    -0.49
    Hochspringen
    -0.48
    +#+#
    -0.47
    naya
    -0.47
    POSITIVE LOGITS
     minors
    0.80
     minor
    0.70
     Minor
    0.70
    Minor
    0.65
    minor
    0.64
    hoeddwyd
    0.63
     dependents
    0.59
     underage
    0.59
    UserScript
    0.57
     TestBed
    0.56
    Activations Density 4.424%

    No Known Activations