© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197646
    Prev
    Next
    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     лока
    0.40
    妸
    0.39
     deles
    0.38
    ὸς
    0.38
    不了
    0.37
     QnrB
    0.37
    ອກ
    0.36
     nanof
    0.36
    chrono
    0.35
    Occup
    0.35
    POSITIVE LOGITS
     D
    0.47
     Merchandise
    0.44
     Tm
    0.44
    edom
    0.43
    athom
    0.43
     Thur
    0.40
     Thom
    0.40
     DOM
    0.39
    car
    0.38
     gero
    0.38
    Activations Density 0.000%

    No Known Activations