© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57208
    Prev
    Next
    INDEX
    Explanations

    French postal codes and department codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferritin
    0.56
     agglut
    0.52
     faculties
    0.52
     पावसा
    0.52
    ักษ
    0.50
     scrutin
    0.50
    ära
    0.50
    閬
    0.50
     presses
    0.49
    qvist
    0.49
    POSITIVE LOGITS
     साइड
    0.57
    teaching
    0.56
    group
    0.55
     accompagne
    0.54
    SIDE
    0.53
    Side
    0.52
    י
    0.52
    i
    0.52
     côté
    0.51
    French
    0.51
    Activations Density 0.004%

    No Known Activations