© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4776
    Prev
    Next
    INDEX
    Explanations

    words or sequences of words that signify actions or events that have already occurred

    oai_token-act-pair · gemini-2.0-flash

    Doing or creating

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.85
    
    -0.83
    Personensuche
    -0.76
     garcía
    -0.69
     EconPapers
    -0.68
     myſelf
    -0.68
     itſelf
    -0.67
     Shakspeare
    -0.67
     themſelves
    -0.67
     auffi
    -0.67
    POSITIVE LOGITS
     the
    1.11
     those
    0.56
    The
    0.47
    Those
    0.47
     The
    0.47
    //</
    0.45
    those
    0.45
     olan
    0.44
     these
    0.44
     this
    0.43
    Activations Density 4.700%

    No Known Activations