© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6836
    Prev
    Next
    INDEX
    Explanations

    code snippets that load external JavaScript and CSS files

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    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
     createState
    -0.66
    SpringRunner
    -0.60
    VIAF
    -0.58
    ParallelGroup
    -0.54
    SBATCH
    -0.52
    sects
    -0.52
    ChildScrollView
    -0.52
    irei
    -0.52
     pró
    -0.51
     Arms
    -0.50
    POSITIVE LOGITS
    Portail
    0.58
     تضيفلها
    0.56
    enol
    0.50
    multicolumn
    0.47
    出版年
    0.45
    DrawerToggle
    0.45
    ImageContext
    0.44
     ComVisible
    0.43
    theless
    0.43
     Tiberius
    0.43
    Activations Density 0.599%

    No Known Activations