© 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. 9464
    Prev
    Next
    INDEX
    Explanations

    snippets of code

    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
    Negative Logits
    ">//
    -0.52
    ages
    -0.51
     anticipating
    -0.48
     anticipation
    -0.48
    オリティ
    -0.48
    colgroup
    -0.47
    lemmer
    -0.45
    znego
    -0.44
    kelijk
    -0.43
    Tikang
    -0.43
    POSITIVE LOGITS
     '*':
    0.62
     فريبيس
    0.61
     ainfi
    0.60
     Theſe
    0.60
     Distribu
    0.59
     Abroad
    0.58
     GenerationType
    0.56
    Soorten
    0.56
    })));
    0.54
     Beſ
    0.54
    Activations Density 11.149%

    No Known Activations