© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9638
    Prev
    Next
    INDEX
    Explanations

    code snippets from various languages, especially C++, Javascript, and Go, identifying syntax elements like parentheses, brackets, operators, and keywords

    oai_token-act-pair · gemini-2.0-flash

    tokens with unusual or non-standard characters

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

    Code snippets

    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
     vi
    -0.67
     v
    -0.65
     st
    -0.62
     tra
    -0.62
     ar
    -0.60
     b
    -0.60
    %',
    -0.60
    %'
    -0.60
     B
    -0.60
     r
    -0.60
    POSITIVE LOGITS
     crdi
    0.91
     itſelf
    0.88
     myſelf
    0.73
     Monfieur
    0.73
     greateſt
    0.72
     cdti
    0.71
     ovp
    0.70
     raiſ
    0.69
     sportback
    0.69
     pleaſure
    0.69
    Activations Density 3.463%

    No Known Activations