© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8186
    Prev
    Next
    INDEX
    Explanations

    mentions of nominations and the US Senate

    oai_token-act-pair · gemini-2.0-flash

    job selection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    FormTagHelper
    -0.65
    abstractmethod
    -0.57
    Personensuche
    -0.57
    InputTagHelper
    -0.56
     AssemblyCulture
    -0.56
    يديا
    -0.56
     nobile
    -0.55
     poveznice
    -0.55
    ParallelGroup
    -0.54
     estekak
    -0.54
    POSITIVE LOGITS
     selection
    1.45
     Selection
    1.31
     appointment
    1.23
     selecting
    1.23
    Selection
    1.23
    selection
    1.18
    Selecting
    1.13
     appoint
    1.12
     selections
    1.11
     SELECTION
    1.10
    Activations Density 1.221%

    No Known Activations