© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14139
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, specifically football, players, defense and contracts

    oai_token-act-pair · gemini-2.0-flash

    defense or contract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    BufferException
    -0.67
    Bakgrunnsstoff
    -0.63
    ValueStyle
    -0.63
     Majefty
    -0.61
    EventQueue
    -0.60
     beſt
    -0.60
     AssemblyProduct
    -0.60
     sulfuric
    -0.59
     cauſe
    -0.57
    المكان
    -0.57
    POSITIVE LOGITS
    <bos>
    0.84
     autorytatywna
    0.76
    ↵↵
    0.62
    ChildScrollView
    0.53
    AnchorTagHelper
    0.52
    verwijspagina
    0.52
    ล่า
    0.51
    </h2>
    0.49
     In
    0.49
    onAttach
    0.49
    Activations Density 0.637%

    No Known Activations