© 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. 31821
    Prev
    Next
    INDEX
    Explanations

    what

    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
    stub
    0.42
     Stub
    0.41
     stub
    0.41
    獃
    0.39
     hib
    0.39
    ៩
    0.38
     പതി
    0.37
    เผย
    0.37
    烫
    0.36
    asty
    0.36
    POSITIVE LOGITS
     what
    0.57
     whats
    0.56
     vad
    0.53
     What
    0.52
     wat
    0.51
     mikä
    0.50
    what
    0.48
     WHAT
    0.47
    Whats
    0.45
     Which
    0.45
    Activations Density 0.006%

    No Known Activations