© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5037
    Prev
    Next
    INDEX
    Explanations

    content from different knowledge domains, including software testing, project management, and food, while also identifying names.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ***!
    -0.75
     تانيه
    -0.60
    تقاوى
    -0.58
     NgModule
    -0.58
    !*\
    -0.56
     EconPapers
    -0.56
    KeySpec
    -0.55
    Slf
    -0.54
    примеча
    -0.53
    ScopeManager
    -0.53
    POSITIVE LOGITS
    География
    0.54
     Kecil
    0.50
    Obrázky
    0.49
     Bupati
    0.49
     onCancelled
    0.45
     positifs
    0.45
     quelquefois
    0.45
     دریافت‌شده
    0.44
     förr
    0.44
     igång
    0.44
    Activations Density 3.578%

    No Known Activations