© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    Latin words and phrases, with some exceptions

    oai_token-act-pair · gemini-2.0-flash

    legal/medical document snippets

    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
     
    -0.62
    ,
    -0.58
    -
    -0.55
    .
    -0.49
    <bos>
    -0.47
    /
    -0.47
     out
    -0.46
    \
    -0.44
    and
    -0.43
     i
    -0.42
    POSITIVE LOGITS
    ^(@)
    0.90
     lenker
    0.84
     محفوظة
    0.81
     iconFacebook
    0.80
    uxxxx
    0.78
     (\<
    0.77
    VersionUID
    0.77
     BorderSide
    0.76
     Forumite
    0.75
    InputTagHelper
    0.74
    Activations Density 0.773%

    No Known Activations