© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12908
    Prev
    Next
    INDEX
    Explanations

    earrings, jewelry, rings

    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_13_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
    $\
    0.59
     שי
    0.55
    Vin
    0.53
     hymns
    0.52
    Blessed
    0.52
    Romans
    0.50
    statistics
    0.50
     Prayers
    0.50
     பாபிலோ
    0.49
    Ocean
    0.49
    POSITIVE LOGITS
    莢
    0.47
     கொண்டு
    0.46
     जाएंगे
    0.46
     ABO
    0.45
    LAY
    0.45
     Прав
    0.44
     caf
    0.44
     knives
    0.44
    STO
    0.44
     carc
    0.44
    Activations Density 0.001%

    No Known Activations