© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 551
    Prev
    Next
    INDEX
    Explanations

    words that are parts of medical or scientific reports

    oai_token-act-pair · gemini-2.0-flash

    organizational, joint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joint
    -0.82
     Joint
    -0.81
    Joint
    -0.75
    broad
    -0.74
    joint
    -0.70
     broad
    -0.69
     JOINT
    -0.68
     Joints
    -0.65
     Broad
    -0.61
    Broad
    -0.60
    POSITIVE LOGITS
     AssemblyCulture
    0.60
    JvmStatic
    0.59
     Crisp
    0.55
     مشين
    0.54
    AntiForgeryToken
    0.54
     pulumi
    0.54
    ValueStyle
    0.53
     Nix
    0.53
     Roskov
    0.52
    District
    0.52
    Activations Density 9.704%

    No Known Activations