© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    the words "artificial", "natural", and anything containing "mut" in the context of saliva

    oai_token-act-pair · gemini-2.0-flash

    artificial

    np_max-act · gemini-2.0-flash

    artificial

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     present
    -0.67
     particular
    -0.65
     not
    -0.63
     Champ
    -0.62
     gros
    -0.62
    ⓘ
    -0.61
     final
    -0.60
    ımı
    -0.60
     familiar
    -0.60
     able
    -0.60
    POSITIVE LOGITS
     elettrica
    0.91
     Efq
    0.90
     Houſe
    0.88
     Theſe
    0.88
     Reſ
    0.87
     varandra
    0.84
     photolibrary
    0.84
     figliu
    0.82
     Jefus
    0.82
     Diſ
    0.82
    Activations Density 1.110%

    No Known Activations