© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3825
    Prev
    Next
    INDEX
    Explanations

    the word "in" or phrases "under" or "Apache"

    oai_token-act-pair · gemini-2.0-flash

    prepositions "in" and "under"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -1.05
     myſelf
    -1.00
     itſelf
    -0.96
     raiſ
    -0.85
     becauſe
    -0.84
     themſelves
    -0.81
     againſt
    -0.81
     uſed
    -0.81
     дописавши
    -0.80
     vectorielle
    -0.78
    POSITIVE LOGITS
    <bos>
    0.62
    <eos>
    0.61
    [
    0.54
     proib
    0.52
    @
    0.48
    {\
    0.48
    台
    0.47
    {
    0.46
    (()
    0.45
    ẵng
    0.45
    Activations Density 0.816%

    No Known Activations