© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223737
    Prev
    Next
    INDEX
    Explanations

    "old man" followed by Tiber or Hemlock

    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_10_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
    1
    0.89
    it
    0.87
    ot
    0.84
    new
    0.80
     Ambassadors
    0.79
    0
    0.79
     Antibodies
    0.76
    für
    0.75
    b
    0.73
    bies
    0.73
    POSITIVE LOGITS
     retinal
    0.80
     reduction
    0.77
     prudent
    0.75
     gastric
    0.72
     circuit
    0.72
     rodent
    0.70
     router
    0.69
     diet
    0.69
     decreased
    0.69
     remar
    0.69
    Activations Density 0.005%

    No Known Activations