© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10158
    Prev
    Next
    INDEX
    Explanations

    text in research papers with figure references, mentions of simulations, and data analysis

    oai_token-act-pair · gemini-2.0-flash

    colors

    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
    Solid
    -0.65
     Solid
    -0.63
     sólidos
    -0.55
     solid
    -0.52
    solid
    -0.51
     assurent
    -0.50
    NewUrlParser
    -0.50
     découver
    -0.47
     debout
    -0.46
     aisladas
    -0.46
    POSITIVE LOGITS
     colors
    0.85
     color
    0.85
     colour
    0.74
     Colors
    0.73
     colours
    0.71
    ScopeManager
    0.70
     colored
    0.67
    BASEPATH
    0.65
     Color
    0.65
    colored
    0.62
    Activations Density 14.332%

    No Known Activations