© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5991
    Prev
    Next
    INDEX
    Explanations

    pop up, pop-up, populating, pop culture

    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_39_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
     마치
    0.43
    备份
    0.41
    нет
    0.39
     ASK
    0.39
     COMPUT
    0.37
    नात
    0.36
    坯
    0.36
    мі
    0.36
    obb
    0.36
    டக்க
    0.36
    POSITIVE LOGITS
     पॉप
    0.65
     pop
    0.61
     Pop
    0.57
    Pop
    0.55
     popul
    0.53
    ポップ
    0.52
     popping
    0.52
    pop
    0.50
     POP
    0.48
     poplar
    0.47
    Activations Density 0.005%

    No Known Activations