© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13058
    Prev
    Next
    INDEX
    Explanations

    the past participles of the words "take" and "go."

    oai_token-act-pair · gemini-2.0-flash

    Leaving/removing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    StoryboardSegue
    -1.23
    AndEndTag
    -1.21
     CreateTagHelper
    -1.16
    findpost
    -0.98
    parsedMessage
    -0.98
     EconPapers
    -0.95
    NameInMap
    -0.94
     NSCoder
    -0.94
    +:+
    -0.93
     Efq
    -0.93
    POSITIVE LOGITS
     took
    0.93
     did
    0.83
     went
    0.77
     take
    0.74
     got
    0.71
     takes
    0.69
     taking
    0.69
      
    0.67
     do
    0.67
     '
    0.65
    Activations Density 0.112%

    No Known Activations