© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    words attributed to speakers or authors

    oai_token-act-pair · 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
    <eos>
    -0.66
     intptr
    -0.58
    ↵
    -0.52
    </strong>
    -0.51
     "
    -0.50
    *
    -0.46
     
    -0.46
    <em>
    -0.46
    ↵↵
    -0.44
    ickness
    -0.43
    POSITIVE LOGITS
    вгений
    0.83
    ConstraintMaker
    0.79
     endwhile
    0.79
     itſelf
    0.78
    ContentAsync
    0.73
     AssemblyProduct
    0.71
    zugehen
    0.70
    seamnă
    0.68
     NDEBUG
    0.68
     (\<
    0.68
    Activations Density 8.771%

    No Known Activations