© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    scientific and common names of plants and animals, plus some similar words like wood

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    jsdelivr
    -0.63
    Facades
    -0.61
    Sao
    -0.56
     Sao
    -0.55
    庁
    -0.54
     @"/
    -0.52
    MessageTagHelper
    -0.52
    ugc
    -0.52
     GenerationType
    -0.52
    semantics
    -0.52
    POSITIVE LOGITS
    లాలు
    0.53
    Amicalement
    0.53
    AutoField
    0.52
    nito
    0.48
    منابع
    0.48
     klubu
    0.48
     pleaſure
    0.48
    Imágenes
    0.47
    ReusableCell
    0.47
    bundet
    0.45
    Activations Density 2.925%

    No Known Activations