© 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. 8143
    Prev
    Next
    INDEX
    Explanations

    words associated with making important decisions

    oai_token-act-pair · gemini-2.0-flash

    decision

    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
    Manbalar
    -0.52
    $_['
    -0.50
     jScrollPane
    -0.48
    basicConfig
    -0.47
    Clik
    -0.47
     snippetHide
    -0.45
    rue
    -0.44
    WriteTagHelper
    -0.43
    Collegamenti
    -0.41
    FTFY
    -0.41
    POSITIVE LOGITS
     decision
    2.67
    decision
    2.47
     Decision
    2.33
    Decision
    2.31
     decisions
    2.28
     DECISION
    2.17
    Decisions
    2.13
     Decisions
    2.11
    decisions
    2.06
     décision
    1.97
    Activations Density 1.107%

    No Known Activations