© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    jama
    0.39
    J
    0.39
     Musk
    0.38
     jama
    0.38
    vee
    0.38
    ინა
    0.38
    ereum
    0.37
     j
    0.36
     jaws
    0.36
    iglas
    0.36
    POSITIVE LOGITS
     G
    0.55
    หล
    0.46
     Rochester
    0.45
     루
    0.44
     Г
    0.43
     Hob
    0.41
     گ
    0.41
     રસ
    0.41
    Roche
    0.40
     Temple
    0.39
    Activations Density 0.000%

    No Known Activations