© 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. 29981
    Prev
    Next
    INDEX
    Explanations

    Vadodara, Pakistan, Soweto, Bismarck

    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
    t
    0.46
    d
    0.39
    aj
    0.37
    د
    0.36
     and
    0.34
    r
    0.34
    ب
    0.33
    aw
    0.32
    ai
    0.31
    ก
    0.30
    POSITIVE LOGITS
     consulte
    0.27
     musia
    0.25
     outperform
    0.24
     warriors
    0.24
     havoc
    0.24
     gameplay
    0.23
     ако
    0.23
     firepower
    0.23
     synapse
    0.23
    :
    0.22
    Activations Density 0.002%

    No Known Activations