© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    sections containing summaries, conclusions, or discussions of scientific papers

    oai_token-act-pair · gemini-2.0-flash

    Actions in the past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    yntaxException
    -0.68
    ">//
    -0.67
    rungsseite
    -0.64
     henvisninger
    -0.62
     intptr
    -0.62
    曖昧さ回避
    -0.60
    MockBean
    -0.59
    Gön
    -0.58
     HttpHeaders
    -0.57
    apimachinery
    -0.57
    POSITIVE LOGITS
     contenus
    0.46
     balanceOf
    0.46
    VILLE
    0.46
    KommentareTeilen
    0.44
    ville
    0.44
    </caption>
    0.44
    ScopeManager
    0.43
    
    0.43
     contenidos
    0.42
     responsáveis
    0.42
    Activations Density 1.364%

    No Known Activations