© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 13399
    Prev
    Next
    INDEX
    Explanations

    a mix of event-related terms and specific words, seemingly without a clear unifying theme

    oai_token-act-pair · 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
    </em>
    -0.79
    </strong>
    -0.65
    </h5>
    -0.64
    </s>
    -0.61
    </h2>
    -0.60
     and
    -0.59
    </i>
    -0.57
    ness
    -0.57
    <s>
    -0.56
     but
    -0.56
    POSITIVE LOGITS
     fermés
    1.07
     vectorielles
    0.97
     StatelessWidget
    0.97
     africains
    0.94
     définiti
    0.92
     الحره
    0.92
     avoient
    0.91
    ⓧ
    0.90
     découver
    0.90
     énergé
    0.89
    Activations Density 0.648%

    No Known Activations