© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9453
    Prev
    Next
    INDEX
    Explanations

    instances of explaining, interpreting and describing things

    oai_token-act-pair · gemini-2.0-flash

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     explain
    -1.18
     explained
    -1.08
     explanation
    -1.07
     explains
    -1.05
    explain
    -1.02
     explaining
    -1.02
     Explain
    -1.00
    explained
    -0.96
     explica
    -0.96
    Explain
    -0.95
    POSITIVE LOGITS
    UserScript
    0.74
     препратки
    0.74
    AsUp
    0.68
     Roskov
    0.63
    InsertCommand
    0.59
    TypedDataSet
    0.57
     useAppContext
    0.56
     ―――――
    0.55
    IBarButtonItem
    0.54
    iterrane
    0.53
    Activations Density 13.671%

    No Known Activations