© 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. 159127
    Prev
    Next
    INDEX
    Explanations

    M

    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
    iseau
    0.43
     ladd
    0.39
    ሞ
    0.39
    enge
    0.38
    PlatformImage
    0.37
    न्ध
    0.37
     reemplazar
    0.36
    ensional
    0.35
     एप्प
    0.35
     AppCompat
    0.35
    POSITIVE LOGITS
     M
    1.22
     الم
    0.80
     М
    0.76
     एम
    0.59
    M
    0.58
     Fl
    0.56
    Ｍ
    0.52
     Mullen
    0.50
     muc
    0.46
    ミュ
    0.45
    Activations Density 0.000%

    No Known Activations