© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10700
    Prev
    Next
    INDEX
    Explanations

    technical or scientific language within documents

    oai_token-act-pair · gemini-2.0-flash

    genetic studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NullCheck
    -0.64
    ViewFeatures
    -0.61
    الحياه
    -0.59
     CURIAM
    -0.58
    Rüyada
    -0.57
     متعلقه
    -0.57
    webElementGuid
    -0.56
    jsdelivr
    -0.56
     correctes
    -0.55
    NameInMap
    -0.55
    POSITIVE LOGITS
     twin
    0.54
    twin
    0.53
     Twin
    0.50
    Twin
    0.50
    ItemBackground
    0.48
    +)$
    0.47
     Unito
    0.46
     lập
    0.46
    abre
    0.46
    candidate
    0.46
    Activations Density 2.083%

    No Known Activations