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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33265
    Prev
    Next
    INDEX
    Explanations

    quote endings

    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
    ysets
    0.39
    ੍ਹਾਂ
    0.38
     नृत्य
    0.38
    砣
    0.38
     নৃত্য
    0.37
     ইত্যাদি
    0.36
    摩擦
    0.36
    ក្រោម
    0.36
    ṁ
    0.35
    xxx
    0.35
    POSITIVE LOGITS
    zym
    0.35
     Vai
    0.35
    SAND
    0.35
    ড্রিম
    0.35
     Sandals
    0.35
     جل
    0.34
     вой
    0.33
     žel
    0.33
    agio
    0.33
     চর্
    0.33
    Activations Density 0.001%

    No Known Activations