© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    substrings specific to font awesome icons, especially those representing states like "unfinished" or "plus/minus"

    oai_token-act-pair · gemini-2.0-flash

    archaic/foreign words

    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
     
    -0.59
     Bob
    -0.56
     [
    -0.53
     in
    -0.52
     L
    -0.52
     E
    -0.52
     is
    -0.52
     over
    -0.51
     Bo
    -0.51
     K
    -0.50
    POSITIVE LOGITS
     surla
    1.04
     pleaſure
    1.00
     Monfieur
    0.98
     purpoſe
    0.97
     Anſ
    0.96
     transfieras
    0.95
     itſelf
    0.92
     themſelves
    0.90
     Majefty
    0.90
     leaſt
    0.89
    Activations Density 0.454%

    No Known Activations