© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5026
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or numbers

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    Not in Any Lists

    No Comments

    Negative Logits
     so
    -1.24
     Efq
    -0.97
     linkovi
    -0.80
     ſo
    -0.79
     myſelf
    -0.75
    so
    -0.74
     sooooo
    -0.74
     soooo
    -0.73
    InjectAttribute
    -0.73
     sooo
    -0.73
    POSITIVE LOGITS
     V
    0.66
    V
    0.57
    Su
    0.57
    Do
    0.57
     Su
    0.56
     L
    0.55
     thus
    0.54
    do
    0.54
    su
    0.54
     therefore
    0.52
    Activations Density 1.131%

    No Known Activations