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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7855
    Prev
    Next
    INDEX
    Explanations

    certain suffixes that frequently appear at the end of words and abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    mille

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     tasche
    -0.74
    twimg
    -0.71
     soggior
    -0.69
     mukana
    -0.68
    ollectionView
    -0.68
     preghi
    -0.67
     jopa
    -0.67
     Shakspeare
    -0.66
    SpringBootTest
    -0.66
     morire
    -0.65
    POSITIVE LOGITS
     חיצוניים
    0.75
    RegressionTest
    0.69
    حياتها
    0.64
    TAKT
    0.62
     continúas
    0.60
    Haben
    0.59
    Посилання
    0.59
     las
    0.59
    hooter
    0.57
    adpleegd
    0.56
    Activations Density 0.156%

    No Known Activations