© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203881
    Prev
    Next
    INDEX
    Explanations

    upward rifle, shoot, Iron Palm

    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_37_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
     swords
    1.04
     sword
    0.92
    剑
    0.88
    劍
    0.84
     Swords
    0.82
     slashing
    0.82
     blade
    0.81
    刀
    0.79
     blades
    0.78
     तलवार
    0.77
    POSITIVE LOGITS
     στε
    0.41
    邵
    0.40
     scolaire
    0.39
     القاهرة
    0.38
     ἐ
    0.37
     ಶಾ
    0.37
     штат
    0.37
     educators
    0.37
    俘
    0.37
     जुर्माना
    0.36
    Activations Density 0.027%

    No Known Activations