© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5524
    Prev
    Next
    INDEX
    Explanations

    discourse markers, especially those indicating causality or explanation

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    WebVitals
    -0.66
     himo
    -0.57
    ammlung
    -0.57
     nakalista
    -0.55
    <bos>
    -0.54
    contentLoaded
    -0.52
    riwal
    -0.52
    ագրություններ
    -0.49
    րջ
    -0.49
     comigo
    -0.48
    POSITIVE LOGITS
     way
    0.94
    Accordingly
    0.73
    Consequently
    0.71
     vậy
    0.69
     accordingly
    0.65
     Consequently
    0.63
    Way
    0.62
    way
    0.61
    这样
    0.60
     disso
    0.60
    Activations Density 2.064%

    No Known Activations