© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13120
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating frustration and questions about what to do, alongside references to specific applications or technical concepts.

    oai_token-act-pair · gemini-2.0-flash

    conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     InputDecoration
    -0.67
    ItemBackground
    -0.66
     stanovnika
    -0.66
     protoimpl
    -0.65
     ComVisible
    -0.61
    WithMany
    -0.61
    titch
    -0.55
    Extinguishing
    -0.54
    dibles
    -0.52
     asynchronously
    -0.52
    POSITIVE LOGITS
    脚注の使い方
    0.58
    ratory
    0.50
    íncia
    0.50
     المعيارى
    0.49
     بيها
    0.48
    errat
    0.48
    logr
    0.48
     halfway
    0.47
     telling
    0.47
     ena
    0.46
    Activations Density 2.956%

    No Known Activations