© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40548
    Prev
    Next
    INDEX
    Explanations

    ()

    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_57_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
    |$
    0.46
    ңыз
    0.42
    pyrazin
    0.42
    みの
    0.41
    legends
    0.39
    azam
    0.38
    өп
    0.38
     intensa
    0.37
    navigationLinks
    0.37
    FT
    0.37
    POSITIVE LOGITS
     عدد
    0.42
    عدد
    0.40
    +}
    0.39
     po
    0.38
     Pes
    0.38
     Zahl
    0.37
     soles
    0.37
     Numero
    0.37
     lie
    0.36
     car
    0.36
    Activations Density 0.001%

    No Known Activations