© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11364
    Prev
    Next
    INDEX
    Explanations

    narratives and descriptions of events and conflicts.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to data structure terminology

    np_token-act-pair-logits · gpt-4o-mini

    Changes and developments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     becoming
    -1.90
     become
    -1.82
     becomes
    -1.79
     Become
    -1.74
    becoming
    -1.73
    become
    -1.70
     Becoming
    -1.67
     became
    -1.65
     Becomes
    -1.56
    becomes
    -1.54
    POSITIVE LOGITS
    OGND
    0.69
    ंदीखरीदारी
    0.62
     AssemblyProduct
    0.62
     للاسماء
    0.60
     CreateTagHelper
    0.59
    AccessorTable
    0.59
    はじめに
    0.59
    complexType
    0.57
     تانيه
    0.57
    Przypisy
    0.56
    Activations Density 1.560%

    No Known Activations