© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13875
    Prev
    Next
    INDEX
    Explanations

    the word "population" and its plural form

    oai_token-act-pair · gemini-2.0-flash

    population

    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
    Negative Logits
     population
    -2.41
    population
    -1.91
     Population
    -1.89
    Population
    -1.81
     populations
    -1.55
     POPULATION
    -1.53
     población
    -1.18
    populations
    -1.16
     popula
    -1.16
     Populations
    -1.15
    POSITIVE LOGITS
    parsedMessage
    1.02
    tvguidetime
    1.00
    ThroughAttribute
    0.96
     indisponible
    0.96
     nakalista
    0.94
    IsContent
    0.94
     GenerationType
    0.90
    AddTagHelper
    0.90
    #+#
    0.89
     يتيمه
    0.89
    Activations Density 0.857%

    No Known Activations