© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64897
    Prev
    Next
    INDEX
    Explanations

    Doctors Without Borders

    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_51_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
    pon
    0.40
    ிரம்
    0.39
    oplankton
    0.38
    ogli
    0.38
    itsa
    0.38
    ABL
    0.38
    plect
    0.37
    Fle
    0.37
    avon
    0.37
    :].
    0.36
    POSITIVE LOGITS
    ks
    0.75
    ্ক
    0.65
    كة
    0.61
    ket
    0.59
    ke
    0.59
    ky
    0.56
    ké
    0.55
    kas
    0.55
    kien
    0.55
    k
    0.54
    Activations Density 0.000%

    No Known Activations