© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    the word "belong", and somewhat relatedly the word "money", along with technical vocabulary related to physics and finance

    oai_token-act-pair · 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
     
    -1.04
     I
    -1.03
     the
    -1.02
     a
    -1.00
     (
    -0.97
     <
    -0.91
     [
    -0.85
     "
    -0.84
     J
    -0.84
     my
    -0.84
    POSITIVE LOGITS
     Efq
    2.50
     myſelf
    2.22
     itſelf
    2.22
     Jefus
    2.20
     Majefty
    2.09
     Monfieur
    2.09
    ſelf
    2.05
    ſelves
    2.02
     pleaſure
    1.95
     raiſ
    1.94
    Activations Density 0.827%

    No Known Activations