© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15864
    Prev
    Next
    INDEX
    Explanations

    angle brackets and the keyword "wait" in code

    oai_token-act-pair · gemini-2.0-flash

    "<"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -2.16
     Efq
    -2.08
     Majefty
    -2.03
     myſelf
    -1.95
     pleaſure
    -1.92
     raiſ
    -1.92
     Monfieur
    -1.88
     faſt
    -1.85
     themſelves
    -1.84
     doubtnut
    -1.79
    POSITIVE LOGITS
     
    1.20
     I
    1.05
     '
    1.02
     S
    1.01
     "
    1.00
     the
    0.91
      
    0.91
     M
    0.90
     (
    0.88
     C
    0.87
    Activations Density 0.155%

    No Known Activations