© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4409
    Prev
    Next
    INDEX
    Explanations

    named, awarded, recognized, won, received

    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
     выигра
    0.50
     победи
    0.50
     zwycię
    0.50
     승
    0.48
    winners
    0.48
     winner
    0.47
    Winner
    0.47
    winner
    0.47
     winners
    0.46
     wins
    0.45
    POSITIVE LOGITS
     sot
    0.41
     desal
    0.38
    enarios
    0.37
    ない
    0.37
     evolution
    0.36
    รู้จัก
    0.36
    备
    0.36
     projected
    0.35
    อบ
    0.35
     counsel
    0.34
    Activations Density 0.026%

    No Known Activations