© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6328
    Prev
    Next
    INDEX
    Explanations

    documents containing legal language relating to citizenship

    oai_token-act-pair · gemini-2.0-flash

    citizen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     שוליים
    -0.71
    Przypisy
    -0.69
    fseek
    -0.68
    authorised
    -0.68
     MotionEvent
    -0.66
     venons
    -0.65
     Enquiry
    -0.65
     intptr
    -0.64
    Quellen
    -0.64
     enqu
    -0.64
    POSITIVE LOGITS
    <bos>
    0.64
    —
    0.59
    ization
    0.59
     betweenstory
    0.59
    Toward
    0.57
     maș
    0.57
    ized
    0.56
    —”
    0.56
     cauza
    0.55
     bipartisan
    0.55
    Activations Density 0.834%

    No Known Activations