© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12275
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash

    command-line arguments Method used: 1 — because top activating tokens are argument variables like "argv"/"args"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    )*
    -0.50
     ...
    -0.48
    ),
    -0.47
    ...
    -0.47
     (
    -0.46
    )
    -0.46
     \
    -0.46
      
    -0.46
     .
    -0.46
     -
    -0.44
    POSITIVE LOGITS
     Мексичка
    1.25
    WithIOException
    1.05
     AssemblyCulture
    1.04
    ⓧ
    1.03
    +#+#
    1.03
     betweenstory
    1.03
     Efq
    1.03
     تضيفلها
    1.02
     للمعارف
    1.02
     iſt
    1.00
    Activations Density 3.843%

    No Known Activations