© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121578
    Prev
    Next
    INDEX
    Explanations

    or tea

    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_27_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
    ក
    0.37
    Steam
    0.36
     accord
    0.33
     exception
    0.33
    出来ない
    0.33
    BG
    0.33
     exceptions
    0.33
     faltando
    0.32
    CIS
    0.32
     संस्क
    0.32
    POSITIVE LOGITS
    ides
    0.45
    istere
    0.38
     Marlin
    0.38
    ಿಗಳು
    0.38
    dessus
    0.37
    驽
    0.37
    urers
    0.37
     peroneal
    0.36
    ium
    0.36
    tych
    0.36
    Activations Density 0.003%

    No Known Activations