© 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. 5595
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions within scientific publications

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with a parenthesis

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

    academic citations

    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
     nakalista
    -0.68
    mybatisplus
    -0.67
     препратки
    -0.59
    GEBURTSDATUM
    -0.59
    SharedDtor
    -0.58
     NSCoder
    -0.57
    ніципа
    -0.57
     utafitiHapana
    -0.56
     err
    -0.55
    endregion
    -0.55
    POSITIVE LOGITS
     itſelf
    0.65
     preſ
    0.62
     ſp
    0.60
     uſed
    0.60
     himſelf
    0.60
     myſelf
    0.58
     sauvages
    0.58
     anſ
    0.57
     ſen
    0.56
     obſ
    0.55
    Activations Density 1.343%

    No Known Activations