© 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. 156683
    Prev
    Next
    INDEX
    Explanations

    travel itineraries

    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
     bu
    0.48
     бу
    0.48
    Buffered
    0.47
     Bou
    0.47
    ぶ
    0.47
     bou
    0.46
    Bu
    0.45
     Lift
    0.44
     Buffered
    0.42
     Jú
    0.42
    POSITIVE LOGITS
     CreateWindow
    0.42
    일을
    0.41
     V
    0.40
    روس
    0.38
     VAL
    0.38
     hammer
    0.38
    walla
    0.38
     Vars
    0.38
     Kevin
    0.37
     ngựa
    0.37
    Activations Density 0.000%

    No Known Activations