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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10050
    Prev
    Next
    INDEX
    Explanations

    words associated with gardening

    oai_token-act-pair · gemini-2.0-flash

    garden plants context

    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
    SBATCH
    -0.51
     '\\;'
    -0.50
     enfe
    -0.50
     sánh
    -0.49
    tamol
    -0.49
     typedef
    -0.48
     "'";
    -0.48
     Decoration
    -0.47
     discredit
    -0.47
    endmodule
    -0.46
    POSITIVE LOGITS
    InstrumentedTest
    0.71
    GTCX
    0.65
    Personensuche
    0.61
    Predecesor
    0.54
    spiller
    0.54
    FormTagHelper
    0.53
     herb
    0.51
     passive
    0.50
     border
    0.49
    border
    0.49
    Activations Density 0.988%

    No Known Activations