© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9639
    Prev
    Next
    INDEX
    Explanations

    text related to American football that mentions quarterbacks and injuries

    oai_token-act-pair · gemini-2.0-flash

    Football quarterbacks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.80
     iſt
    -0.65
     jadx
    -0.65
     $_"
    -0.62
     Theſe
    -0.61
     Attila
    -0.59
     Jefus
    -0.59
    ParallelGroup
    -0.59
    MessageOf
    -0.58
     myſelf
    -0.58
    POSITIVE LOGITS
     pet
    0.45
    Референце
    0.40
    Vag
    0.39
     passing
    0.39
     dry
    0.39
     post
    0.39
     ac
    0.39
    ne
    0.38
     Référence
    0.38
    withIdentifier
    0.38
    Activations Density 1.300%

    No Known Activations