© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12760
    Prev
    Next
    INDEX
    Explanations

    instances of the word "describe" and its inflections, alongside related words. That may include negative connotations like complaining

    oai_token-act-pair · gemini-2.0-flash

    describe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     describe
    -1.95
     describes
    -1.82
     describing
    -1.73
     described
    -1.73
    describe
    -1.55
     Describe
    -1.52
     DESCR
    -1.50
     Describes
    -1.46
     description
    -1.41
    Describe
    -1.41
    POSITIVE LOGITS
     propOrder
    0.77
    UnusedPrivate
    0.68
    Bibliograf
    0.62
    errHandler
    0.62
    municipi
    0.61
     Commencez
    0.61
    DispatchToProps
    0.61
    ProcessEvent
    0.60
    verwijspagina
    0.60
    VIAF
    0.60
    Activations Density 0.515%

    No Known Activations