© 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. 10684
    Prev
    Next
    INDEX
    Explanations

    marketing-related content referencing facts, statistics, and reports

    oai_token-act-pair · gemini-2.0-flash

    Reports and statistics

    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
    ља
    -0.43
     offered
    -0.41
     nasel
    -0.40
    пра
    -0.40
    getMinutes
    -0.39
     Hauses
    -0.39
    спа
    -0.38
    Attrs
    -0.38
    fa
    -0.37
    $\
    -0.37
    POSITIVE LOGITS
     通販
    0.75
    Референце
    0.72
    RegistryLite
    0.72
    IUrlHelper
    0.69
     мәкал
    0.69
    }{*}{}
    0.66
     kaarangay
    0.63
     Efq
    0.62
    +#+#
    0.62
     архивлан
    0.62
    Activations Density 0.728%

    No Known Activations