© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    technical or scientific language including references, numbers, and data including medical and transportation

    oai_token-act-pair · gemini-2.0-flash

    Beginning of phrases/sentences

    np_max-act · 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
     Efq
    -0.92
     Theſe
    -0.78
     poffe
    -0.74
     Majefty
    -0.72
     myſelf
    -0.72
     pleaſure
    -0.71
     Anſ
    -0.69
     chofe
    -0.69
    ſelves
    -0.69
     ſte
    -0.69
    POSITIVE LOGITS
    ver
    0.43
    rimir
    0.40
     ja
    0.40
     bağlantılar
    0.40
    朝
    0.40
    anto
    0.40
    ula
    0.39
     so
    0.39
    riz
    0.37
    出す
    0.37
    Activations Density 75.591%

    No Known Activations