© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4610
    Prev
    Next
    INDEX
    Explanations

    pronouns relating to people and forms of the verb "to be," possibly to identify descriptions of people.

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oplayer
    -0.59
    <bos>
    -0.54
    TestBed
    -0.52
     iprot
    -0.50
     bort
    -0.48
    ագրություն
    -0.48
     أعلام
    -0.48
     ruf
    -0.46
    ('=
    -0.46
    ետ
    -0.45
    POSITIVE LOGITS
     Normdatei
    0.65
     AspNetCore
    0.60
    ernalia
    0.57
    
    0.57
     Juga
    0.53
    rungsseite
    0.51
     capitalized
    0.51
    currentColor
    0.50
    hyrchwyd
    0.50
    MemoryWarning
    0.49
    Activations Density 17.826%

    No Known Activations