© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 294
    Prev
    Next
    INDEX
    Explanations

    code snippets/java code

    oai_token-act-pair · gemini-2.0-flash

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -0.88
     مشين
    -0.83
    UnusedPrivate
    -0.80
    NUMX
    -0.77
     Majefty
    -0.75
     Monfieur
    -0.73
    ]--;
    -0.71
    μως
    -0.70
     initComponents
    -0.70
    $.
    -0.69
    POSITIVE LOGITS
    classmethod
    0.57
    staticmethod
    0.56
    static
    0.54
     static
    0.54
    Static
    0.48
     mortes
    0.48
     Static
    0.44
    静态
    0.43
    enk
    0.41
    ことはない
    0.40
    Activations Density 1.572%

    No Known Activations