© 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. 4464
    Prev
    Next
    INDEX
    Explanations

    references to military units and organizations

    oai_token-act-pair · gemini-2.0-flash

    ordinal suffixes

    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
    NewUrlParser
    -0.90
    MigrationBuilder
    -0.88
    WithIOException
    -0.81
    Chham
    -0.75
    AndEndTag
    -0.73
    :✨
    -0.72
    kloped
    -0.72
     '\\;'
    -0.71
    исленность
    -0.69
     nahilalakip
    -0.68
    POSITIVE LOGITS
     Field
    0.46
     S
    0.45
     Fires
    0.42
     mang
    0.41
     coy
    0.39
     às
    0.38
    ş
    0.38
    tront
    0.38
    enged
    0.37
    Field
    0.37
    Activations Density 2.285%

    No Known Activations