© 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. 94183
    Prev
    Next
    INDEX
    Explanations

    7

    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
    <0xB3>
    0.63
     seventh
    0.52
     семи
    0.47
     sétimo
    0.47
     séptimo
    0.46
    ༧
    0.44
     seven
    0.43
     Seven
    0.43
     Seventh
    0.41
    七
    0.41
    POSITIVE LOGITS
    SUM
    0.55
    5
    0.51
    Sum
    0.48
    4
    0.46
    sum
    0.46
    leave
    0.43
    Branch
    0.41
    Princ
    0.41
    NEWS
    0.41
    edi
    0.41
    Activations Density 0.001%

    No Known Activations