© 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. 5630
    Prev
    Next
    INDEX
    Explanations

    LaTeX math delimiters

    oai_token-act-pair · gemini-2.0-flash

    code-related syntax or formatting

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

    {

    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
    com
    -0.42
     ${
    -0.41
    )
    -0.40
    Proxy
    -0.39
     }
    -0.38
    !
    -0.37
    ↵
    -0.37
    .
    -0.36
    点は
    -0.36
    方が
    -0.35
    POSITIVE LOGITS
    berdayakan
    0.84
    NUMX
    0.83
     дописавши
    0.78
     faſt
    0.74
    بوابة
    0.74
    didSet
    0.72
     ddelweddau
    0.71
    ToProps
    0.71
    dây
    0.69
     referrerpolicy
    0.68
    Activations Density 0.502%

    No Known Activations