© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6373
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and discussions of statistics using dollar signs to indicate variables

    oai_token-act-pair · gemini-2.0-flash

    items in a dataset or tabular structure

    np_token-act-pair-logits · gpt-4o-mini

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     lèvres
    -0.95
     vœux
    -0.92
     oreilles
    -0.83
     dieux
    -0.82
     rayures
    -0.81
     blessés
    -0.79
     négociations
    -0.75
     leçons
    -0.74
     chrétiens
    -0.73
     épaules
    -0.73
    POSITIVE LOGITS
     items
    0.67
     cells
    0.66
     records
    0.65
     conditions
    0.64
     objects
    0.63
     rows
    0.63
     applications
    0.63
     documents
    0.62
     flights
    0.61
     calls
    0.60
    Activations Density 13.204%

    No Known Activations