© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    text related to event jobs or handing out materials at a booth

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash

    punctuation

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    "
    -0.48
    [
    -0.38
    “
    -0.37
    \"
    -0.31
     تعدى
    -0.29
    -0.28
    _
    -0.28
    ."
    -0.28
    .
    -0.27
    *
    -0.27
    POSITIVE LOGITS
    QMetaType
    0.75
    GEBURTSDATUM
    0.75
    Personensuche
    0.73
     resourceCulture
    0.71
    AddTagHelper
    0.71
    ValueStyle
    0.71
    цездатний
    0.69
     transfieras
    0.69
    bunch
    0.66
     protoimpl
    0.66
    Activations Density 4.947%
    No Known Activations