© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13320
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that connect a sentence to the previous or subsequent sentences

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · 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
    Negative Logits
     المعيارى
    -0.52
    ত্ত
    -0.45
    年間
    -0.43
    nyttet
    -0.42
    ⓧ
    -0.41
    Glory
    -0.40
    ITIVE
    -0.39
     rady
    -0.39
     سبيل
    -0.39
     protoimpl
    -0.38
    POSITIVE LOGITS
     оригіналу
    0.67
     referrerpolicy
    0.65
    клопе
    0.65
    ftagPool
    0.63
    PhysRevD
    0.62
    HasAnnotation
    0.58
    Rüyada
    0.57
     sauter
    0.56
     AppCompatTheme
    0.53
    IMPORTED
    0.53
    Activations Density 15.124%

    No Known Activations