© 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. 212857
    Prev
    Next
    INDEX
    Explanations

    cryptograph[y] Diffie-Hellman

    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
    бар
    0.41
     ἡ
    0.40
     pq
    0.39
     sigma
    0.39
    ետ
    0.39
     har
    0.38
     সমিতি
    0.38
    チェ
    0.37
    hets
    0.37
     spam
    0.36
    POSITIVE LOGITS
    antil
    0.42
     entrando
    0.42
    僳
    0.38
     Privilege
    0.38
    atil
    0.38
    ilación
    0.37
     पसर
    0.37
    ேன்
    0.36
     بتایا
    0.36
    Pascal
    0.36
    Activations Density 0.000%

    No Known Activations