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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200304
    Prev
    Next
    INDEX
    Explanations

    peach flower

    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
    牰
    0.48
     Hansen
    0.45
    谷
    0.42
     서
    0.42
     書
    0.41
     secur
    0.40
     Whiskey
    0.40
     Schuster
    0.40
     tribal
    0.39
     Sergi
    0.39
    POSITIVE LOGITS
    桃花
    0.60
     peach
    0.59
     hoa
    0.55
    rta
    0.52
    託
    0.52
    桃
    0.51
    Hoa
    0.50
    hoa
    0.50
    టా
    0.47
     Peach
    0.47
    Activations Density 0.001%

    No Known Activations