© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    capitalized terms, proper nouns, and acronyms in a variety of domains

    oai_token-act-pair · gemini-2.0-flash

    DCT

    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
    TagHelper
    -0.54
    expandindo
    -0.54
    rungsseite
    -0.54
     ModelExpression
    -0.51
    anne
    -0.47
    다고
    -0.45
    abestanden
    -0.45
     typelib
    -0.44
    borderSide
    -0.44
     she
    -0.44
    POSITIVE LOGITS
    basicConfig
    0.57
    __(/*!
    0.53
     AppCompatTheme
    0.50
    enumii
    0.50
    InSection
    0.48
    Среди
    0.48
    CppMethod
    0.47
     flesta
    0.47
     Carmine
    0.47
    voorbeeld
    0.46
    Activations Density 2.951%

    No Known Activations