© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18781
    Prev
    Next
    INDEX
    Explanations

    enneagram

    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_34_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
     wojewód
    0.41
    댓
    0.37
     powiat
    0.37
     physiques
    0.37
     neurologist
    0.37
     pedestrians
    0.36
    uteurs
    0.36
     tym
    0.36
     livelihoods
    0.36
     প্রতিবন্ধ
    0.35
    POSITIVE LOGITS
    spirit
    0.39
     പരിശ
    0.38
    Spirit
    0.37
     মূ
    0.36
    ଃ
    0.36
    っている
    0.35
     மூ
    0.35
     pillow
    0.35
    cona
    0.35
     yoğun
    0.35
    Activations Density 0.001%

    No Known Activations