© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13789
    Prev
    Next
    INDEX
    Explanations

    information related to espionage, signals intelligence, and government agencies

    oai_token-act-pair · gemini-2.0-flash

    encryption, codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     دیکھیے
    -0.62
     समीक्षक
    -0.60
    ArrowToggle
    -0.60
     AssemblyProduct
    -0.59
     kasarigan
    -0.58
    geführten
    -0.51
    Domic
    -0.51
    rawDesc
    -0.50
    mphony
    -0.49
    ابت
    -0.49
    POSITIVE LOGITS
     codes
    0.84
     code
    0.82
     Codes
    0.81
     CODE
    0.78
     Code
    0.76
     inde
    0.75
     coded
    0.75
    Codes
    0.70
    Code
    0.70
    code
    0.70
    Activations Density 2.250%

    No Known Activations