© 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. 4587
    Prev
    Next
    INDEX
    Explanations

    the names of people in positions of power

    oai_token-act-pair · gemini-2.0-flash

    important people

    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
    Negative Logits
     Gewinner
    -0.58
     stället
    -0.56
    ırken
    -0.54
    OfWork
    -0.54
     lenker
    -0.50
    escudo
    -0.50
    CRR
    -0.50
    ēju
    -0.50
     Rookie
    -0.50
    ıyordu
    -0.49
    POSITIVE LOGITS
    InputBorder
    0.71
    bootstrapcdn
    0.66
    ReusableCell
    0.62
    DebuggerNonUser
    0.59
    HandlerContext
    0.56
     promin
    0.55
    StatusLabel
    0.53
    onAttach
    0.52
    ]-->
    0.50
    CopyWith
    0.50
    Activations Density 1.079%

    No Known Activations