© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14266
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to criticizing someone for something, especially authorities or companies for financial issues.

    oai_token-act-pair · gemini-2.0-flash

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     low
    -1.03
     Low
    -1.02
     Reduced
    -0.98
    Low
    -0.98
     reduced
    -0.96
     reduce
    -0.94
     reducing
    -0.93
    Reduced
    -0.91
     lowers
    -0.91
     lowering
    -0.91
    POSITIVE LOGITS
     high
    1.27
    high
    1.12
    High
    1.05
     higher
    1.04
     High
    1.02
     HIGH
    0.96
     highest
    0.94
    HIGH
    0.94
     tinggi
    0.93
    Higher
    0.91
    Activations Density 5.649%

    No Known Activations