© 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. 13241
    Prev
    Next
    INDEX
    Explanations

    statistical descriptions of sports games, especially the last or first occurrences of events

    oai_token-act-pair · gemini-2.0-flash

    sports game context

    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
     تضيفلها
    -0.75
     contextLoads
    -0.75
     Shakspeare
    -0.70
     ―――――
    -0.67
    InstrumentedTest
    -0.65
    enzie
    -0.65
     Sleeves
    -0.63
    sidemargin
    -0.63
     doubtnut
    -0.63
     butterknife
    -0.63
    POSITIVE LOGITS
     estekak
    0.55
     s
    0.46
     Roskov
    0.46
    unk
    0.43
    Frame
    0.43
     Civil
    0.42
    frame
    0.41
     civil
    0.41
    os
    0.41
     Flüs
    0.40
    Activations Density 0.539%

    No Known Activations