© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10382
    Prev
    Next
    INDEX
    Explanations

    a mix of French and Spanish personal pronouns and related words like "budget" and "choice."

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    
    -0.91
     resourceCulture
    -0.88
     تضيفلها
    -0.87
     mijne
    -0.87
     myſelf
    -0.86
     houſe
    -0.84
    AndEndTag
    -0.84
     quæ
    -0.84
    setVerticalGroup
    -0.83
    存于互联网档案馆
    -0.82
    POSITIVE LOGITS
     I
    0.50
     di
    0.48
     
    0.46
     sm
    0.46
     sk
    0.44
     n
    0.44
     lo
    0.44
     r
    0.44
     h
    0.43
     tan
    0.43
    Activations Density 0.574%

    No Known Activations