© 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. 3893
    Prev
    Next
    INDEX
    Explanations

    the verb "do" and its conjugations

    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_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
    Doing
    -0.85
     Doing
    -0.84
     DOING
    -0.82
     doing
    -0.80
    doing
    -0.72
     myſelf
    -0.72
    setVerticalGroup
    -0.71
     doin
    -0.68
     himſelf
    -0.67
     itſelf
    -0.67
    POSITIVE LOGITS
    AndroidJUnit
    0.74
     the
    0.71
     how
    0.60
     The
    0.59
    er
    0.59
     where
    0.56
     when
    0.52
     esetben
    0.52
    Kjelder
    0.52
     désigner
    0.52
    Activations Density 0.258%

    No Known Activations