© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12294
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "Because" followed by intensity words

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    findpost
    -0.46
    AutoField
    -0.46
    ьа
    -0.42
    prop
    -0.40
    SpringBootTest
    -0.40
    OrDefault
    -0.39
     PROP
    -0.39
     [*]
    -0.39
    PROP
    -0.37
     prop
    -0.37
    POSITIVE LOGITS
    تقاوى
    0.84
    ThemeOverlay
    0.79
     jsPsych
    0.76
    erdings
    0.75
    GEBURTSDATUM
    0.73
     ddelweddau
    0.73
     @"/
    0.72
    épendance
    0.71
     gynhyrchwyd
    0.70
    ✨:
    0.69
    Activations Density 2.165%

    No Known Activations