© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14974
    Prev
    Next
    INDEX
    Explanations

    dates and words that are components of legal documents

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ArrowToggle
    -0.53
    SharedDtor
    -0.52
     Borja
    -0.52
    Datuak
    -0.50
    Fitment
    -0.50
    GEBURTSDATUM
    -0.49
    IntoConstraints
    -0.49
     waisted
    -0.49
     Apartment
    -0.49
     createState
    -0.49
    POSITIVE LOGITS
    期刊论文
    0.66
    niająca
    0.56
    RefNanny
    0.52
    IENTE
    0.50
    findpost
    0.49
    optarg
    0.48
    ткий
    0.47
     leaſt
    0.47
    })`
    0.47
     useDispatch
    0.46
    Activations Density 15.367%

    No Known Activations