© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12157
    Prev
    Next
    INDEX
    Explanations

    words related to family relations, noble titles, and possibly the letter 'r'

    oai_token-act-pair · gemini-2.0-flash

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     daughter
    -0.80
     dochter
    -0.69
     son
    -0.69
     daughters
    -0.68
     sons
    -0.67
     Daughter
    -0.66
    daughter
    -0.64
     child
    -0.60
    daughters
    -0.59
     children
    -0.58
    POSITIVE LOGITS
    NUMX
    0.80
    PhysRevD
    0.79
     useDispatch
    0.62
    новништво
    0.61
    cokinetics
    0.60
     createState
    0.60
    XmlEnum
    0.60
     HttpHeaders
    0.59
     JAXBElement
    0.59
     OFDb
    0.59
    Activations Density 7.886%

    No Known Activations