© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9146
    Prev
    Next
    INDEX
    Explanations

    words related to morality, faith, and religion

    oai_token-act-pair · gemini-2.0-flash

    marriage and love

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ActivityCompat
    -0.64
    ftagPool
    -0.61
    BackPressed
    -0.51
    SystemColors
    -0.46
    testify
    -0.40
    glColor
    -0.40
     tải
    -0.40
     utama
    -0.40
     Accept
    -0.40
     conf
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.91
    TagMode
    0.74
    HtmlAttribute
    0.70
     distanciation
    0.65
    новниш
    0.64
    SpringBootTest
    0.64
     BrowserModule
    0.62
    UnitTesting
    0.61
    UrlResolution
    0.59
    continence
    0.59
    Activations Density 2.228%

    No Known Activations