© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40687
    Prev
    Next
    INDEX
    Explanations

    nacimiento and nascent

    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_3_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
    ClrBit
    0.66
     vultures
    0.64
     finland
    0.64
    ONEDB
    0.60
     كرد
    0.60
    suivant
    0.59
     vasena
    0.57
     rozwoju
    0.57
    ﾆ
    0.57
    reqParams
    0.56
    POSITIVE LOGITS
    af
    0.80
    z
    0.79
    า
    0.75
    onen
    0.74
    ing
    0.73
    age
    0.72
    ip
    0.72
    å
    0.72
    ation
    0.70
    omm
    0.70
    Activations Density 0.001%

    No Known Activations