© 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. 5717
    Prev
    Next
    INDEX
    Explanations

    text describing multiprocessing code and worker queues, especially when a lock is involved.

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

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

    code, computing, programming

    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
     propOrder
    -0.58
     pinulongan
    -0.53
    :✨
    -0.51
     Colomb
    -0.50
     estimés
    -0.49
     Swarm
    -0.48
     plunge
    -0.47
     bodysuit
    -0.47
    RenderAtEndOf
    -0.46
     bangles
    -0.46
    POSITIVE LOGITS
    ChildScrollView
    0.68
    SourceChecksum
    0.60
     nonatomic
    0.54
    enschappelijke
    0.53
    CloseOperation
    0.53
    saraba
    0.53
    Források
    0.53
    eachtet
    0.53
    sidemargin
    0.52
    inders
    0.50
    Activations Density 15.611%

    No Known Activations