© 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. 2934
    Prev
    Next
    INDEX
    Explanations

    words related to programming across multiple languages

    oai_token-act-pair · gemini-2.0-flash

    quantity and opportunities

    np_token-act-pair-logits · gpt-4o-mini
    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
     AssemblyCulture
    -0.93
    Tikang
    -0.92
     autorytatywna
    -0.86
    +#+#
    -0.82
    GOTREF
    -0.82
     snippetHide
    -0.82
     cherchés
    -0.81
     kasarigan
    -0.81
     transfieras
    -0.81
     '\\;'
    -0.80
    POSITIVE LOGITS
     a
    0.75
     plenty
    0.59
     an
    0.59
     opportunities
    0.52
     more
    0.52
     opportunity
    0.51
     great
    0.50
    ENTY
    0.48
     space
    0.48
     considerable
    0.48
    Activations Density 0.723%

    No Known Activations