© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11374
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of thinking and figuring something out

    oai_token-act-pair · gemini-2.0-flash

    thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    parsedMessage
    -0.55
    SpringRunner
    -0.54
    DaoImpl
    -0.51
    GEBURTSDATUM
    -0.49
    WritableDatabase
    -0.48
    UnknownFieldSet
    -0.48
    PRESA
    -0.47
    TintMode
    -0.47
    ).</
    -0.47
    Nuorodos
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.68
     useState
    0.63
    
    0.60
    useState
    0.57
    Geplaatst
    0.57
    DotNetBar
    0.54
    vastatin
    0.49
     webdriver
    0.48
    Subscriber
    0.48
     MonoBehaviour
    0.48
    Activations Density 1.248%

    No Known Activations