© 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. 12299
    Prev
    Next
    INDEX
    Explanations

    the word "currency", sometimes incorrectly activating on the beginning of the name "Ron".

    oai_token-act-pair · gemini-2.0-flash

    currency

    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
     
    -1.09
    1
    -1.07
    2
    -1.05
    <b>
    -1.04
    3
    -1.03
    <em>
    -0.98
      
    -0.97
    <i>
    -0.96
    <strong>
    -0.96
    ↵↵
    -0.94
    POSITIVE LOGITS
     myſelf
    2.08
     Efq
    2.05
     itſelf
    2.02
     Majefty
    1.98
     Jefus
    1.94
    ^(@)
    1.85
     Monfieur
    1.82
     houſe
    1.76
     purpoſe
    1.74
     himſelf
    1.73
    Activations Density 3.024%

    No Known Activations