© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    terms related to corporations or political entities

    oai_token-act-pair · gemini-2.0-flash

    corporate

    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
    corporate
    -1.30
     corporate
    -1.30
     Corporate
    -1.23
     CORPOR
    -1.20
    Corporate
    -1.18
    CORPOR
    -1.05
    corpor
    -0.96
     corporation
    -0.96
     corpor
    -0.96
     CORPORATION
    -0.93
    POSITIVE LOGITS
    ExtendWith
    0.69
    AsUp
    0.58
    FTFY
    0.56
     stringBy
    0.54
    WithIOException
    0.51
     aikana
    0.50
     cheminée
    0.50
    }));
    0.50
    ("]");
    0.49
    iprot
    0.48
    Activations Density 8.553%

    No Known Activations