© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8168
    Prev
    Next
    INDEX
    Explanations

    sections of text expressing intent to understand or solve problems via collaboration

    oai_token-act-pair · gemini-2.0-flash

    understanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     base
    -0.81
     Base
    -0.57
    base
    -0.57
    NOPQRST
    -0.52
    exitRule
    -0.51
    ̅
    -0.48
     BASE
    -0.47
     Almeida
    -0.46
    Linki
    -0.46
     bases
    -0.44
    POSITIVE LOGITS
     understanding
    0.85
     understands
    0.83
     understand
    0.83
     Understanding
    0.79
    understand
    0.78
    Understanding
    0.75
     understood
    0.75
     finding
    0.75
     Understand
    0.74
    finding
    0.73
    Activations Density 1.903%

    No Known Activations