© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15176
    Prev
    Next
    INDEX
    Explanations

    snippets of various forms of computer code, like html, javascript, and Makefile, plus words like "workaround".

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act-logits · gemini-2.0-flash

    say "work"

    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_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
    UrlResolution
    -0.59
    HideFlags
    -0.55
    Datuak
    -0.53
    :✨
    -0.50
     ©️
    -0.47
    RenderAtEndOf
    -0.46
     néglig
    -0.46
    mybatisplus
    -0.45
    AxisAlignment
    -0.45
     referenties
    -0.45
    POSITIVE LOGITS
     worked
    2.63
     works
    2.56
     working
    2.36
     work
    2.36
    worked
    2.34
     Worked
    2.28
     Works
    2.16
    works
    2.14
    working
    2.13
     WORKS
    2.09
    Activations Density 2.925%

    No Known Activations