© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7768
    Prev
    Next
    INDEX
    Explanations

    the articles and prepositions, and words and phrases related to government, rights, and debate.

    oai_token-act-pair · gemini-2.0-flash

    people, population

    np_max-act-logits · gemini-2.0-flash

    variants of the word "people"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    EndContext
    -0.72
    wpi
    -0.59
     Signalez
    -0.59
    HideFlags
    -0.56
     '\\;'
    -0.56
     iprot
    -0.53
    GetAsync
    -0.53
     старости
    -0.53
    AddHtmlAttribute
    -0.52
    wapV
    -0.52
    POSITIVE LOGITS
     people
    1.67
     population
    1.45
    people
    1.42
    People
    1.28
     People
    1.25
     peoples
    1.21
     populations
    1.21
    population
    1.19
     populace
    1.16
     PEOPLE
    1.16
    Activations Density 1.768%

    No Known Activations