© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60761
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.5-flash-lite

    the verb 'do' when it indicates an action or task.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    0.56
    िंग
    0.50
    ة
    0.46
     this
    0.43
     do
    0.43
    ों
    0.42
     it
    0.42
    ੇ
    0.42
    ുന്ന
    0.41
     said
    0.41
    POSITIVE LOGITS
    qq
    0.51
    xygen
    0.50
    pper
    0.49
    ot
    0.48
    ños
    0.48
    X
    0.48
    от
    0.47
    XI
    0.47
    xt
    0.46
    x
    0.46
    Activations Density 0.004%

    No Known Activations