© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68445
    Prev
    Next
    INDEX
    Explanations

    mole

    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_51_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
    ären
    0.48
     le
    0.42
     方
    0.40
     Lucifer
    0.40
     Fluorescence
    0.40
    édon
    0.40
     જેટ
    0.39
    ær
    0.38
    ule
    0.38
     fluorescent
    0.38
    POSITIVE LOGITS
    SA
    0.44
     кола
    0.43
     plotter
    0.40
     snaps
    0.39
    ग्नो
    0.39
    㕵
    0.38
     гла
    0.38
    찡
    0.38
    DA
    0.38
    oma
    0.38
    Activations Density 0.000%

    No Known Activations