© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian and English words related to greetings and web development

    oai_token-act-pair · gemini-2.0-flash

    multiple languages and code

    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
    GEBURTSDATUM
    -1.17
    ^(@)
    -1.16
     itſelf
    -1.15
    DockStyle
    -1.15
     Efq
    -1.13
    NUMX
    -1.09
     myſelf
    -1.07
     Jefus
    -1.05
    yntaxException
    -1.04
    XmlAccessType
    -1.00
    POSITIVE LOGITS
    mon
    0.55
    tre
    0.54
    bal
    0.48
    ver
    0.46
    gar
    0.46
    tra
    0.46
     R
    0.45
    block
    0.44
    amb
    0.44
    hak
    0.44
    Activations Density 0.592%

    No Known Activations