© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15742
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names in close proximity to statistics or sports terms

    oai_token-act-pair · gemini-2.0-flash

    Identifiers, statistics, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     vya
    -0.59
     touristique
    -0.56
     CURIAM
    -0.54
     izquier
    -0.54
     supérieures
    -0.54
     abstrait
    -0.52
     scolaires
    -0.52
     下午
    -0.52
     sauvages
    -0.51
     تضيفلها
    -0.50
    POSITIVE LOGITS
    ]='\
    0.55
     iprot
    0.55
    SBATCH
    0.53
    TemporalType
    0.50
    סה
    0.45
    MockMvc
    0.43
    multer
    0.43
     radio
    0.43
     Sar
    0.43
    ProcessEvent
    0.43
    Activations Density 0.539%

    No Known Activations