© 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. 11735
    Prev
    Next
    INDEX
    Explanations

    the word "entered" and related words ("enter", "signing", "lawfully")

    oai_token-act-pair · gemini-2.0-flash

    entered

    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
     Monfieur
    -2.19
     myſelf
    -2.13
     Efq
    -2.11
     Jefus
    -2.05
     houſe
    -1.99
     themſelves
    -1.95
     Houſe
    -1.94
     Majefty
    -1.91
     himſelf
    -1.88
     itſelf
    -1.87
    POSITIVE LOGITS
     
    1.05
     I
    1.05
      
    1.03
     B
    1.03
     K
    0.98
     D
    0.96
     P
    0.96
     C
    0.96
     M
    0.94
     R
    0.93
    Activations Density 0.777%

    No Known Activations