© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11249
    Prev
    Next
    INDEX
    Explanations

    words without an easily discernible common meaning or pattern and may require more context for interpretation.

    oai_token-act-pair · gemini-2.0-flash

    two letter abbreviations

    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
     “
    -0.96
     
    -0.90
     d
    -0.90
     ver
    -0.90
     en
    -0.88
     er
    -0.88
     es
    -0.88
     se
    -0.88
     op
    -0.88
     "
    -0.87
    POSITIVE LOGITS
     myſelf
    1.91
     feroit
    1.82
     itſelf
    1.80
     purpoſe
    1.78
     Jefus
    1.76
     Monfieur
    1.73
     Efq
    1.73
     himſelf
    1.70
     houſe
    1.69
     étoient
    1.67
    Activations Density 4.157%

    No Known Activations