© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    descriptions of wrestling matches

    oai_token-act-pair · gemini-2.0-flash

    sports reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     g
    -0.54
     d
    -0.50
     m
    -0.45
     b
    -0.43
     (
    -0.43
     Ahead
    -0.41
     Around
    -0.39
     vin
    -0.38
     we
    -0.37
     pot
    -0.37
    POSITIVE LOGITS
    ValueStyle
    0.87
    ſelf
    0.87
     purpoſe
    0.86
     uſe
    0.83
     fubject
    0.82
    DeleteBehavior
    0.81
     pleaſure
    0.81
     houſe
    0.81
     itſelf
    0.79
     fhort
    0.79
    Activations Density 16.138%

    No Known Activations