© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91203
    Prev
    Next
    INDEX
    Explanations

    emphasis marker

    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_60_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
     I
    0.47
    hit
    0.46
    上方
    0.42
    Hit
    0.41
    taking
    0.39
     hit
    0.39
    codingPath
    0.38
    它
    0.38
     वह
    0.37
     حياة
    0.37
    POSITIVE LOGITS
     acolo
    0.73
     than
    0.66
     allí
    0.64
     dort
    0.60
     Than
    0.57
     there
    0.56
     orada
    0.56
     там
    0.55
     ahí
    0.55
     než
    0.54
    Activations Density 0.005%

    No Known Activations