© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63100
    Prev
    Next
    INDEX
    Explanations

    SS abbreviations

    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_46_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
     deacetyl
    0.35
    তলা
    0.35
     乀
    0.35
     巴
    0.34
     AGRIC
    0.34
     Antenna
    0.34
    化工
    0.34
     antenna
    0.34
    <unused57>
    0.33
     Hä
    0.33
    POSITIVE LOGITS
     SS
    3.06
    SS
    2.80
     ss
    2.80
     एसएस
    2.66
     SSR
    2.53
     Ss
    2.45
     SSC
    2.41
     SSD
    2.38
     SSI
    2.36
     SSA
    2.36
    Activations Density 0.011%

    No Known Activations