© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 665
    Prev
    Next
    INDEX
    Explanations

    words and prefixes that start with "pro-", especially those ending in "-ing", and technical terminology.

    oai_token-act-pair · gemini-2.0-flash

    pro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pro
    -2.98
     Pro
    -2.73
    Pro
    -2.69
    pro
    -2.56
     PRO
    -2.14
    PRO
    -2.08
     pros
    -1.61
    プロ
    -1.52
     Pros
    -1.45
    Pros
    -1.39
    POSITIVE LOGITS
    
    0.81
     Efq
    0.78
     Houſe
    0.76
     myſelf
    0.74
    berdayakan
    0.71
    owników
    0.70
     Theſe
    0.69
     mapStateToProps
    0.69
    ópez
    0.69
     يتيمه
    0.69
    Activations Density 4.966%

    No Known Activations