© 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. 14717
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to historical events, settlements, and religious practices.

    oai_token-act-pair · gemini-2.0-flash

    historical, folklore objects

    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
     Paglinawan
    -0.69
    ">@
    -0.62
     Signalez
    -0.59
    eseorang
    -0.57
    脚注の使い方
    -0.55
    })$}
    -0.55
    ритори
    -0.55
    $}}
    -0.54
    >");
    -0.54
    PasswordEncoder
    -0.53
    POSITIVE LOGITS
    -
    0.60
    parsedMessage
    0.54
    IsContent
    0.50
    NameInMap
    0.50
    setViewName
    0.50
    Cyfeiriadau
    0.49
     initComponents
    0.48
     نمایید
    0.46
    InSection
    0.45
     Sobald
    0.45
    Activations Density 2.615%

    No Known Activations