© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed", names ending in "ed", and words ending in "ing" that also have a word after them starting with the letter "s"

    oai_token-act-pair · gemini-2.0-flash

    ed

    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
    ed
    -2.75
    ED
    -1.94
     Anſ
    -1.48
     Monfieur
    -1.46
     pleaſure
    -1.45
     myſelf
    -1.45
     itſelf
    -1.43
     ſever
    -1.40
     raiſ
    -1.39
     houſe
    -1.39
    POSITIVE LOGITS
    <bos>
    0.96
    ↵↵
    0.93
    ↵
    0.85
    <eos>
    0.79
     a
    0.73
    ↵↵↵
    0.73
      
    0.69
     -
    0.68
     in
    0.66
     was
    0.65
    Activations Density 2.803%

    No Known Activations