© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13052
    Prev
    Next
    INDEX
    Explanations

    terms specific to legal language, academic writing, and cultural traditions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    NameInMap
    -0.57
     חיצוניים
    -0.47
    IContainer
    -0.46
    SharedCtor
    -0.45
     nevo
    -0.44
     AssemblyCulture
    -0.42
    EXISTS
    -0.42
    исленность
    -0.41
    ChromeDriver
    -0.41
    apnews
    -0.41
    POSITIVE LOGITS
     الحره
    0.71
     propOrder
    0.70
    Pratique
    0.70
    CppCodeGen
    0.68
    MENAFN
    0.64
    uttgart
    0.64
     godine
    0.59
    Portale
    0.57
     sekali
    0.57
    anches
    0.56
    Activations Density 12.112%

    No Known Activations