© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2946
    Prev
    Next
    INDEX
    Explanations

    phrases describing conflicting viewpoints or arrangements

    oai_token-act-pair · gemini-2.0-flash

    opposites

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     buy
    -2.53
    buy
    -2.34
     Buy
    -2.14
     buying
    -2.13
    Buy
    -2.08
     buys
    -2.06
     BUY
    -1.97
     bought
    -1.95
    buying
    -1.92
    BUY
    -1.89
    POSITIVE LOGITS
     op
    0.98
    Op
    0.89
    op
    0.88
     di
    0.87
     polar
    0.86
     Op
    0.84
     OP
    0.74
     pol
    0.74
    OP
    0.71
    polar
    0.69
    Activations Density 1.095%

    No Known Activations