© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233336
    Prev
    Next
    INDEX
    Explanations

    Holy Land, Christianity, Jerusalem

    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_32_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
     المسي
    0.42
     pilgr
    0.40
     religione
    0.40
     pilgrimage
    0.40
    耶路撒
    0.39
     religious
    0.39
     فلسطين
    0.38
    💍
    0.38
     религиоз
    0.38
     chrét
    0.37
    POSITIVE LOGITS
    मुना
    0.40
     tốc
    0.39
     Columbus
    0.38
    BREAK
    0.37
     kır
    0.37
    ibfk
    0.37
    breaks
    0.37
    倒
    0.37
     cooking
    0.36
     सेवन
    0.36
    Activations Density 0.000%

    No Known Activations