© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149757
    Prev
    Next
    INDEX
    Explanations

    asterisks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     Not
    0.62
     Compens
    0.59
     this
    0.55
     Similarly
    0.54
    this
    0.50
     Even
    0.47
    ↵
    0.45
     Numer
    0.45
     wellknown
    0.45
     For
    0.44
    POSITIVE LOGITS
     =
    0.63
     $=$
    0.57
    =
    0.53
     \&
    0.51
     &\
    0.49
    "=
    0.48
    =\
    0.46
     hides
    0.45
     $=\
    0.45
    \}
    0.45
    Activations Density 0.012%

    No Known Activations