© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12856
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are important and/or formal to a particular context.

    oai_token-act-pair · gemini-2.0-flash

    computing/technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ↵
    -0.59
    ↵↵↵
    -0.57
    ↵↵
    -0.56
    n
    -0.55
    ↵↵↵↵↵
    -0.52
    </strong>
    -0.50
    ↵↵↵↵
    -0.50
    <eos>
    -0.49
     
    -0.49
     calendriers
    -0.48
    POSITIVE LOGITS
     myſelf
    0.77
     whoſe
    0.75
     nahilalakip
    0.72
     Eſ
    0.69
     itſelf
    0.69
     Efq
    0.69
     faſt
    0.68
     proprement
    0.68
     himſelf
    0.66
     Theſe
    0.66
    Activations Density 28.616%

    No Known Activations