© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33487
    Prev
    Next
    INDEX
    Explanations

    f

    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
     Edson
    0.45
     DataLoader
    0.38
     Wilton
    0.38
    Mand
    0.37
    ؍
    0.36
     gav
    0.36
    انس
    0.35
     boyut
    0.35
    ⃣
    0.35
    аны
    0.34
    POSITIVE LOGITS
     f
    1.46
     ف
    1.07
     F
    1.05
     ফ
    1.02
     फ
    0.89
     ฟ
    0.85
    f
    0.84
     ф
    0.84
    F
    0.78
    ฟ
    0.76
    Activations Density 0.004%

    No Known Activations