© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15369
    Prev
    Next
    INDEX
    Explanations

    a wide variety of terms, but often those expressing a personal opinion or judgement

    oai_token-act-pair · gemini-2.0-flash

    Random text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ­
    -0.56
    dro
    -0.55
     Waray
    -0.52
    uf
    -0.51
    Dro
    -0.50
     beginnetje
    -0.49
    bak
    -0.48
    krat
    -0.48
    bal
    -0.47
     Marac
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.71
     ddelweddau
    0.69
     الرياضيه
    0.68
    enumi
    0.68
    ANCIAL
    0.65
    ducted
    0.64
     بيها
    0.62
    MessageOf
    0.61
    drawal
    0.61
    icked
    0.61
    Activations Density 6.018%

    No Known Activations