© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15404
    Prev
    Next
    INDEX
    Explanations

    chemical compound names

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds and their derivatives

    np_token-act-pair-logits · gpt-4o-mini

    organic chemistry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Viitteet
    -0.75
     ReSharper
    -0.74
     useAppContext
    -0.65
     Мексичка
    -0.61
    ,‎
    -0.61
    CopyWith
    -0.61
    Matin
    -0.60
    تقاوى
    -0.60
     PDI
    -0.59
    omitempty
    -0.58
    POSITIVE LOGITS
    DOCTYPE
    0.46
     pinulongan
    0.45
    atta
    0.42
    tinyos
    0.42
     artesanales
    0.41
    Hand
    0.40
     ruok
    0.39
    لينكات
    0.39
     ilma
    0.39
    ThroughAttribute
    0.39
    Activations Density 0.910%

    No Known Activations