© 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. 369
    Prev
    Next
    INDEX
    Explanations

    abbreviations and the prefix "piv"

    oai_token-act-pair · gemini-2.0-flash

    Three letter initialisms

    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
    try
    -0.82
     try
    -0.76
     tries
    -0.75
     Tries
    -0.67
    Try
    -0.67
    tries
    -0.61
    TRY
    -0.60
     trying
    -0.57
     Try
    -0.57
    Tries
    -0.57
    POSITIVE LOGITS
    OTO
    0.61
    UTO
    0.61
    migrationBuilder
    0.60
    ato
    0.60
    TOMS
    0.59
    oto
    0.58
     utafitiHapana
    0.58
    ATO
    0.58
     ota
    0.58
    otu
    0.58
    Activations Density 2.138%

    No Known Activations