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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10271
    Prev
    Next
    INDEX
    Explanations

    mentions of spans of years

    oai_token-act-pair · gemini-2.0-flash

    time periods

    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
     hundred
    -0.74
    hundred
    -0.70
    Clik
    -0.69
    Hundred
    -0.67
     Hundred
    -0.66
     century
    -0.65
    WaitGroup
    -0.64
    urang
    -0.63
    windowFixed
    -0.62
    ViewInit
    -0.60
    POSITIVE LOGITS
    Dec
    0.56
     Byp
    0.50
     Dec
    0.50
    Indented
    0.50
     deca
    0.49
     decades
    0.49
     للمعارف
    0.48
    Las
    0.48
    ßig
    0.48
     Jahr
    0.47
    Activations Density 2.367%

    No Known Activations