© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11451
    Prev
    Next
    INDEX
    Explanations

    various types of parentheses or brackets in code and text snippets.

    oai_token-act-pair · gemini-2.0-flash

    parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Hand
    -0.59
     Cart
    -0.59
     ویکی‌پدیای
    -0.55
    inery
    -0.54
     Sieg
    -0.53
     Dand
    -0.53
     HAND
    -0.52
     bug
    -0.52
    #+#
    -0.51
    CART
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
     utafitiHapana
    0.61
     GenerationType
    0.61
    UnusedPrivate
    0.59
     '\\;'
    0.59
    <bos>
    0.55
     esiste
    0.52
     asti
    0.49
     Jérusalem
    0.49
    ఔ
    0.49
    Activations Density 4.691%

    No Known Activations