© 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
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15916
    Prev
    Next
    INDEX
    Explanations

    institutions connected by 'and'

    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_34_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
    ovel
    0.44
    BufOffset
    0.43
    ਔ
    0.40
     కృ
    0.40
    стройства
    0.39
     convolutions
    0.39
    ネル
    0.39
    MovieList
    0.38
    จับ
    0.38
    örder
    0.37
    POSITIVE LOGITS
    맑
    0.39
     chess
    0.37
     rung
    0.36
    牛奶
    0.35
    roth
    0.34
     Cesare
    0.34
    chess
    0.34
     Tuc
    0.34
     Jersey
    0.34
     Boeing
    0.34
    Activations Density 0.003%

    No Known Activations