© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    words related to programming, especially C++ and Java

    oai_token-act-pair · gemini-2.0-flash

    code structures and programming elements

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

    code

    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
     sobě
    -0.53
     varandra
    -0.50
     nostru
    -0.49
     preuves
    -0.48
     énergé
    -0.47
     africaine
    -0.46
     sexuales
    -0.46
     extérieures
    -0.45
     alimentaires
    -0.45
     scolaires
    -0.44
    POSITIVE LOGITS
    Rè
    0.74
    hnia
    0.72
     initComponents
    0.72
    ViewFeatures
    0.69
     propOrder
    0.68
    յու
    0.63
    ilight
    0.62
    λλην
    0.61
     asn
    0.60
    älde
    0.59
    Activations Density 3.892%

    No Known Activations