© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7584
    Prev
    Next
    INDEX
    Explanations

    it's

    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_39_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
     deseo
    0.50
    宜
    0.45
     бажа
    0.44
     advisable
    0.43
     ваше
    0.43
     жела
    0.43
     ваш
    0.42
     treba
    0.41
     вашу
    0.41
     વિચાર
    0.41
    POSITIVE LOGITS
    팡
    0.39
     dependent
    0.38
     Johns
    0.38
    cius
    0.37
    centes
    0.36
    Cols
    0.36
    hemia
    0.36
     השי
    0.35
    hent
    0.34
    ceptor
    0.33
    Activations Density 0.095%

    No Known Activations