© 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. 16298
    Prev
    Next
    INDEX
    Explanations

    helper verbs that precede verbs

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     void
    -0.48
     بال
    -0.47
    boiling
    -0.47
    клопе
    -0.44
     effort
    -0.42
     efforts
    -0.42
     הה
    -0.42
    hsan
    -0.41
    omock
    -0.41
     tid
    -0.40
    POSITIVE LOGITS
     myſelf
    0.84
     itſelf
    0.82
     himſelf
    0.79
     becauſe
    0.79
     raiſ
    0.79
    WriteTagHelper
    0.79
    ^(@)
    0.78
    存于互联网档案馆
    0.78
     reaſon
    0.77
    ſelf
    0.76
    Activations Density 4.171%

    No Known Activations