© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10729
    Prev
    Next
    INDEX
    Explanations

    words and symbols commonly used in mathematical or physics formulas

    oai_token-act-pair · gemini-2.0-flash

    terms related to definitions

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

    In

    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
     للمعارف
    -0.98
    RenderAtEndOf
    -0.80
    UnsafeEnabled
    -0.79
     CreateTagHelper
    -0.78
     beginnetje
    -0.76
    awtextra
    -0.76
     defaultstate
    -0.72
     createState
    -0.72
     ThemeData
    -0.70
     ویکی‌پدی
    -0.69
    POSITIVE LOGITS
     term
    0.66
     terms
    0.53
    term
    0.52
     terme
    0.47
     Term
    0.46
     Giải
    0.46
    Term
    0.45
     усе
    0.44
    terms
    0.43
     termos
    0.42
    Activations Density 4.819%

    No Known Activations