© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9902
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measure

    oai_token-act-pair · gemini-2.0-flash

    measurements and numbers

    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
    TabIndex
    -0.67
     AssemblyCompany
    -0.61
    MigrationBuilder
    -0.59
    complexType
    -0.58
    enumi
    -0.58
     MILL
    -0.54
    enumii
    -0.53
    はじめに
    -0.51
    olymer
    -0.50
    سطس
    -0.49
    POSITIVE LOGITS
     hundred
    0.65
    hundred
    0.61
    PerformLayout
    0.60
     Hundred
    0.59
     hundreds
    0.52
    Бележки
    0.52
     Seventy
    0.51
     eighty
    0.51
     seventy
    0.51
    Hundred
    0.50
    Activations Density 1.645%

    No Known Activations