© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    parts of code that declare variables, constants, and maps, with some weaker matches related to HTTP headers, error handling, and syscalls.

    oai_token-act-pair · gemini-2.0-flash

    code syntax elements and variable declarations

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

    assignment operators

    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
     null
    -0.57
    }{*}{
    -0.54
     endregion
    -0.52
    queryInterface
    -0.52
     {*}
    -0.50
    ագրություններ
    -0.50
    jsxFileName
    -0.47
    BLANK
    -0.47
    olulu
    -0.46
     IntPtr
    -0.46
    POSITIVE LOGITS
    AccessorTable
    0.69
    ьаж
    0.58
     makeStyles
    0.54
    UnusedPrivate
    0.54
     الدولى
    0.53
    httphttps
    0.51
     dominion
    0.50
     fills
    0.50
     Réponses
    0.50
    mitives
    0.50
    Activations Density 1.511%

    No Known Activations