© 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. 13429
    Prev
    Next
    INDEX
    Explanations

    academic science and medical terminology and associated sentence structure

    oai_token-act-pair · gemini-2.0-flash

    complexity

    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
     complexity
    -0.96
    complexity
    -0.91
     complejidad
    -0.85
     Complexity
    -0.83
    Complexity
    -0.83
     complexities
    -0.82
     Complex
    -0.80
    Complex
    -0.80
     easier
    -0.78
    EndContext
    -0.77
    POSITIVE LOGITS
    eleste
    0.63
    Sprint
    0.53
    tır
    0.53
    sprint
    0.52
     Sprint
    0.52
    queryInterface
    0.51
     naturally
    0.50
    ρεσ
    0.50
     العنوان
    0.49
     noft
    0.49
    Activations Density 23.135%

    No Known Activations