© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14616
    Prev
    Next
    INDEX
    Explanations

    phrases that start and end with the same letter

    oai_token-act-pair · gemini-2.0-flash

    star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.62
     NDEBUG
    -0.61
     Vikipedi
    -0.57
     nakalista
    -0.55
     ویکی‌پدیا
    -0.52
     permanent
    -0.50
     println
    -0.50
     strdup
    -0.50
     Sando
    -0.49
     Thirteen
    -0.48
    POSITIVE LOGITS
    :✨
    0.88
    IntoConstraints
    0.82
    UnusedPrivate
    0.73
    setVerticalGroup
    0.71
     GenerationType
    0.71
    SpringBootTest
    0.70
     preferências
    0.68
    aarrggbb
    0.65
    djangoproject
    0.60
    bkz
    0.59
    Activations Density 0.970%

    No Known Activations