© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 205
    Prev
    Next
    INDEX
    Explanations

    words used in arguments or discussions, including data like numbers or measurements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    jons
    -0.42
    ]
    -0.39
    APR
    -0.38
    WebVitals
    -0.38
     est
    -0.38
    ')[
    -0.38
    likler
    -0.37
    jonen
    -0.36
    ")[
    -0.36
    著
    -0.36
    POSITIVE LOGITS
    Personensuche
    0.86
    WriteTagHelper
    0.84
     كومونز
    0.80
     Normdatei
    0.77
    EDEFAULT
    0.73
     onCreateView
    0.73
    تقاوى
    0.71
    GEBURTSDATUM
    0.71
    MigrationBuilder
    0.71
    lccn
    0.71
    Activations Density 53.947%

    No Known Activations