© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5045
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, specifically those related to data types and conversion

    oai_token-act-pair · gemini-2.0-flash

    programming functions and data types

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

    Int

    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
    vensko
    -0.51
    AccessorTable
    -0.45
    wrt
    -0.43
    matchCondition
    -0.43
    intracht
    -0.42
     plezier
    -0.42
    eber
    -0.42
     mit
    -0.41
    if
    -0.41
    transfer
    -0.41
    POSITIVE LOGITS
     doInBackground
    0.88
    NUMX
    0.79
    BufferException
    0.75
     ExecuteAsync
    0.75
     InputDecoration
    0.70
    ChildScrollView
    0.69
     ujednoznacz
    0.69
    ագրություններ
    0.68
    cshtml
    0.67
    GraphicsUnit
    0.66
    Activations Density 2.006%

    No Known Activations