© 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. 7929
    Prev
    Next
    INDEX
    Explanations

    legal citations and names of judges

    oai_token-act-pair · gemini-2.0-flash

    curiam

    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
    ^(@)
    -1.32
    $.
    -1.19
     $_"
    -1.08
    ^(@
    -1.06
    .}~\
    -1.05
    spesies
    -1.03
    URLException
    -1.02
    ⎓
    -1.01
    olesale
    -1.00
     ―――――
    -0.99
    POSITIVE LOGITS
    <bos>
    1.98
    '
    1.18
    ↵↵
    1.17
    ↵
    1.02
    ’
    0.93
    <eos>
    0.85
      
    0.79
        
    0.79
    S
    0.77
    (
    0.74
    Activations Density 2.565%

    No Known Activations