© 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. 9398
    Prev
    Next
    INDEX
    Explanations

    words related to agriculture, land, water bodies like lakes, rivers, streams, or rain, ecosystems and moisture

    oai_token-act-pair · gemini-2.0-flash

    science and nature

    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
     Meksiku
    -0.58
    mybatisplus
    -0.56
    verifyException
    -0.56
     fidélité
    -0.55
    RetentionPolicy
    -0.54
     définiti
    -0.54
     négatif
    -0.52
     outdoor
    -0.52
     environmental
    -0.51
    Портали
    -0.51
    POSITIVE LOGITS
     BorderRadius
    0.53
    AsUp
    0.52
    OLUTION
    0.51
    PRWEB
    0.51
     TextAppearance
    0.50
     shops
    0.50
    äsent
    0.50
     consultato
    0.49
    ولات
    0.48
    odenal
    0.48
    Activations Density 1.331%

    No Known Activations