© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13358
    Prev
    Next
    INDEX
    Explanations

    US postal addresses

    oai_token-act-pair · gemini-2.0-flash

    US state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    getActiveSheet
    -0.45
    onClose
    -0.45
    SharedCtor
    -0.44
     tiszt
    -0.44
    хой
    -0.43
    тельства
    -0.43
    ThemeOverlay
    -0.42
    ktı
    -0.42
    bcryptjs
    -0.42
    ICIAL
    -0.42
    POSITIVE LOGITS
    клопе
    0.72
     snippetHide
    0.71
    SBATCH
    0.65
     AssemblyCulture
    0.64
     Paglinawan
    0.63
    TagMode
    0.59
    NOPQRST
    0.58
    IonicModule
    0.56
    +#+#
    0.56
    ArrowToggle
    0.56
    Activations Density 0.200%

    No Known Activations