© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74606
    Prev
    Next
    INDEX
    Explanations

    data keys/fields

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    neighbor
    0.43
    sciences
    0.41
     risks
    0.39
    neighbors
    0.39
     जोखिम
    0.38
    Neighbors
    0.37
    እ
    0.37
     neighbors
    0.37
    ẻ
    0.36
    汛
    0.36
    POSITIVE LOGITS
     包括
    0.37
    
    0.36
     Parlamento
    0.35
    umento
    0.35
     immunosupp
    0.35
    摄
    0.34
     уго
    0.34
     EPA
    0.34
     concili
    0.33
     pluck
    0.33
    Activations Density 0.001%

    No Known Activations