© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5215
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially from multiple languages (C, Swift, etc.) and technical documentation.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — tokens mostly start with "▁"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.52
     Par
    -1.16
     Har
    -1.13
    WithIOException
    -1.10
     Gre
    -1.09
    NameInMap
    -1.09
     Ver
    -1.08
     Gu
    -1.08
     Mag
    -1.07
     Bur
    -1.06
    POSITIVE LOGITS
     chrétien
    1.66
     abstrait
    1.60
     religieuses
    1.51
     religieuse
    1.49
     étranger
    1.48
     purpoſe
    1.47
     ſtate
    1.45
     sauvages
    1.40
     enfans
    1.39
     ainfi
    1.38
    Activations Density 25.221%

    No Known Activations