© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5592
    Prev
    Next
    INDEX
    Explanations

    the word "benefit" along with the verbs "come" and "do."

    oai_token-act-pair · gemini-2.0-flash

    benefit

    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
     célè
    -0.75
     destinées
    -0.75
    OOTDTY
    -0.75
     étoient
    -0.73
    WebElementEntity
    -0.73
     hyö
    -0.72
     aDecoder
    -0.72
    dflare
    -0.70
     élas
    -0.70
    GraphicsUnit
    -0.70
    POSITIVE LOGITS
    li
    0.54
    FullPath
    0.52
    es
    0.52
    z
    0.51
    tal
    0.51
    is
    0.50
     Staff
    0.49
     ido
    0.49
     operator
    0.48
    mo
    0.48
    Activations Density 0.166%

    No Known Activations