© 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. 155725
    Prev
    Next
    INDEX
    Explanations

    informal chat Greetings

    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
     Wings
    0.53
     Working
    0.47
    Wings
    0.43
     পঞ্চাশ
    0.42
     Ná
    0.42
     Am
    0.41
     Wolverines
    0.41
     Not
    0.41
     Ам
    0.41
     A
    0.40
    POSITIVE LOGITS
     drinking
    0.51
     than
    0.50
    up
    0.46
    \
    0.46
     text
    0.44
    \...
    0.44
    See
    0.43
     drink
    0.42
    reson
    0.41
     resent
    0.41
    Activations Density 0.005%

    No Known Activations