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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228875
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     الح
    0.64
     الل
    0.60
     اله
    0.58
    الح
    0.57
     L
    0.55
     U
    0.52
    اله
    0.51
     الع
    0.50
     הח
    0.50
     الب
    0.49
    POSITIVE LOGITS
     الم
    0.42
     M
    0.41
     hacked
    0.40
     hitch
    0.40
    jia
    0.40
    המ
    0.38
     М
    0.38
     गेंदों
    0.38
     המ
    0.37
    复杂的
    0.37
    Activations Density 0.000%

    No Known Activations