© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247237
    Prev
    Next
    INDEX
    Explanations

    next or nexus followed by cloud or ify

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adal
    0.41
     Studio
    0.40
    捅
    0.38
     Hassan
    0.38
     Tote
    0.37
     अजि
    0.37
    Studio
    0.36
     Tubular
    0.36
     дорогие
    0.35
     શક્ય
    0.35
    POSITIVE LOGITS
     уйный
    0.39
     NEX
    0.39
     faucibus
    0.38
    "،
    0.38
    츄
    0.38
     þei
    0.38
     टीचिंग
    0.38
     aproape
    0.37
    '",
    0.37
    utility
    0.36
    Activations Density 0.001%

    No Known Activations