© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167287
    Prev
    Next
    INDEX
    Explanations

    double-slit experiment

    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_31_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
     끝
    0.46
     ดี
    0.43
     सब्सक्राइब
    0.42
     absur
    0.41
     पाह
    0.40
     डिज
    0.39
    낍
    0.38
     perfekte
    0.38
    뺄
    0.38
     അദ്ദേഹം
    0.38
    POSITIVE LOGITS
     Seren
    0.38
     Northwest
    0.38
    臊
    0.37
     Yam
    0.36
     Maire
    0.36
    arthritis
    0.36
     chemicals
    0.35
     Wals
    0.35
    やり
    0.34
     passages
    0.34
    Activations Density 0.006%

    No Known Activations