© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4303
    Prev
    Next
    INDEX
    Explanations

    instances of pronouns referring to groups of people

    oai_token-act-pair · gemini-2.0-flash

    They

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    has
    -0.66
    Has
    -0.63
     Has
    -0.55
     it
    -0.47
    waits
    -0.43
     has
    -0.42
     geografia
    -0.41
     temperatuur
    -0.40
    ,
    -0.39
     
    -0.38
    POSITIVE LOGITS
     are
    1.35
     were
    1.33
     weren
    1.02
     WERE
    1.01
     aren
    0.98
    were
    0.89
     arent
    0.89
    ViewFeatures
    0.88
     have
    0.86
     ARE
    0.86
    Activations Density 2.834%

    No Known Activations