© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217712
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_50_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
     Nevis
    0.43
     LIVE
    0.40
     Pasar
    0.40
     yeh
    0.38
     Chil
    0.38
    )+"]
    0.38
     Shipping
    0.38
     Prisoner
    0.38
     β
    0.38
     Treatment
    0.37
    POSITIVE LOGITS
    pinch
    0.44
    acceptable
    0.39
    IONS
    0.36
    bathtub
    0.36
    மையாக
    0.36
    CHREIB
    0.36
    Els
    0.36
    構
    0.36
    כי
    0.35
    ከሰ
    0.35
    Activations Density 0.003%

    No Known Activations