© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35877
    Prev
    Next
    INDEX
    Explanations

    contemplation, contemplative

    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_7_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
    :
    1.09
    ம்
    0.92
     monologue
    0.90
    :“
    0.89
     savez
    0.88
    ில்
    0.87
     queda
    0.87
    い
    0.86
     compara
    0.86
     contigo
    0.86
    POSITIVE LOGITS
     I
    1.27
     to
    1.21
    kh
    1.11
    tt
    1.09
    bc
    1.09
    ll
    1.06
     of
    1.05
    lu
    0.98
    to
    0.96
    rc
    0.96
    Activations Density 0.001%

    No Known Activations