© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 274
    Prev
    Next
    INDEX
    Explanations

    we are / we have / we will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     nás
    0.37
    arlo
    0.34
    URATION
    0.32
     мы
    0.31
    橐
    0.30
     szüks
    0.30
    pJ
    0.30
    Impress
    0.30
    ণ
    0.30
    emon
    0.29
    POSITIVE LOGITS
     समझते
    0.40
     have
    0.37
    evaluate
    0.37
     specialise
    0.37
     decided
    0.36
     получили
    0.36
     провели
    0.36
     Ways
    0.36
     проводят
    0.36
     hadden
    0.35
    Activations Density 0.024%

    No Known Activations