© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12585
    Prev
    Next
    INDEX
    Explanations

    the verb "do" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Efq
    -0.82
    apunov
    -0.78
     pleaſure
    -0.71
     @}
    -0.70
     ſtate
    -0.68
    原始内容存档于
    -0.67
     deſt
    -0.67
     houſe
    -0.66
     becauſe
    -0.66
     preſent
    -0.66
    POSITIVE LOGITS
     done
    0.85
    <bos>
    0.85
     ostavi
    0.80
     doing
    0.75
     do
    0.73
    Doing
    0.69
    
    0.66
     Do
    0.65
    done
    0.65
    Do
    0.63
    Activations Density 0.152%

    No Known Activations