© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8047
    Prev
    Next
    INDEX
    Explanations

    general words appearing amongst technical jargon, especially in healthcare or programming contexts

    oai_token-act-pair · gemini-2.0-flash

    medical patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     InputDecoration
    -0.68
    UrlResolution
    -0.67
     Meksiku
    -0.67
     ***/
    -0.66
     calendriers
    -0.65
     Daß
    -0.62
    ulsory
    -0.61
     myſelf
    -0.60
    AddHtmlAttribute
    -0.60
     snippetHide
    -0.59
    POSITIVE LOGITS
    Configurer
    0.46
    herzog
    0.46
     Fast
    0.46
    ↵↵
    0.44
     rodea
    0.43
    FilterChain
    0.42
     потом
    0.42
    Fast
    0.41
     Autorizaciones
    0.41
    issex
    0.40
    Activations Density 3.198%

    No Known Activations