© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15425
    Prev
    Next
    INDEX
    Explanations

    language related to American football team activities

    oai_token-act-pair · gemini-2.0-flash

    NFL offseason/training

    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
    rrggbb
    -0.46
    GraphicsUnit
    -0.44
     при
    -0.42
     Mar
    -0.41
     raised
    -0.40
    jface
    -0.39
    icho
    -0.39
    aleg
    -0.39
    aarrggbb
    -0.39
    به
    -0.38
    POSITIVE LOGITS
    urlpatterns
    0.71
    Portály
    0.69
     BoxDecoration
    0.65
    IonicModule
    0.65
    脚注の使い方
    0.64
    Filmografie
    0.63
    Filmographie
    0.63
     InputDecoration
    0.63
    delmi
    0.63
     Egli
    0.62
    Activations Density 1.123%

    No Known Activations