© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119069
    Prev
    Next
    INDEX
    Explanations

    reflection/prism

    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_38_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
     Sinh
    0.44
     sinh
    0.41
     GEN
    0.40
    ᱡ
    0.39
     basketball
    0.38
     HEX
    0.38
     adsor
    0.38
     birth
    0.37
     pik
    0.37
     compensated
    0.37
    POSITIVE LOGITS
     rifless
    0.44
    葷
    0.38
    Reflection
    0.37
     Reflection
    0.37
     refle
    0.37
    WidgetItem
    0.37
     reflections
    0.36
     प्रिज्म
    0.36
    ◤
    0.35
    反射
    0.35
    Activations Density 0.004%

    No Known Activations