© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14845
    Prev
    Next
    INDEX
    Explanations

    botanical and horticultural information, including names of societies, awards, and manuals

    oai_token-act-pair · gemini-2.0-flash

    Creative or instructional content

    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
     виправивши
    -0.83
    ViewImports
    -0.77
    SequentialGroup
    -0.72
    RegistryLite
    -0.65
     onCancelled
    -0.63
     tartalomajánló
    -0.56
    aarrggbb
    -0.55
     BoxDecoration
    -0.54
     MainAxisSize
    -0.54
    ObjectContext
    -0.53
    POSITIVE LOGITS
    Modern
    0.48
    Learn
    0.47
    MODERN
    0.44
    GRect
    0.44
    Imagine
    0.44
     popo
    0.43
     tuition
    0.43
     assi
    0.43
     estimés
    0.43
    learn
    0.42
    Activations Density 2.354%

    No Known Activations