© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15721
    Prev
    Next
    INDEX
    Explanations

    spanish language code snippets and general programming terms

    oai_token-act-pair · gemini-2.0-flash

    mixed language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CPT
    -0.51
    CPtr
    -0.49
     CPL
    -0.47
     an
    -0.47
     any
    -0.46
     (
    -0.45
    ladel
    -0.43
     EconPapers
    -0.41
    postolic
    -0.41
     due
    -0.40
    POSITIVE LOGITS
     enfans
    0.82
     stället
    0.78
     disambiguazione
    0.76
     picioare
    0.76
     Theſe
    0.75
     Hongrie
    0.75
     quæ
    0.74
     vectorielles
    0.74
     flesta
    0.71
     leçon
    0.71
    Activations Density 0.594%

    No Known Activations