© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    legal jargon and scientific text with mentions of 'in vivo' and 'in vitro'

    oai_token-act-pair · gemini-2.0-flash

    legal and scientific terms

    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
    Negative Logits
     myſelf
    -2.03
     pleaſure
    -2.02
     Efq
    -1.92
     itſelf
    -1.88
     iſt
    -1.83
     Monfieur
    -1.83
     purpoſe
    -1.79
     Reſ
    -1.78
     Majefty
    -1.73
     ſtate
    -1.72
    POSITIVE LOGITS
     ad
    1.21
     de
    1.18
     pro
    1.16
     ex
    1.09
     en
    0.98
     du
    0.91
     et
    0.88
     d
    0.88
     
    0.85
     par
    0.83
    Activations Density 3.543%

    No Known Activations