© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3078
    Prev
    Next
    INDEX
    Explanations

    The Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     \%
    0.69
    ра
    0.64
     /
    0.62
    ות
    0.60
     \;
    0.59
     তোলে
    0.59
    utables
    0.58
     -
    0.57
    ">
    0.57
     от
    0.56
    POSITIVE LOGITS
     miserably
    0.78
    קה
    0.78
    heureusement
    0.77
    Ironically
    0.75
    okra
    0.75
    संस्करण
    0.74
     quieran
    0.72
    ﻪ
    0.72
    ﺤ
    0.71
    fortunately
    0.71
    Activations Density 0.016%

    No Known Activations