© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4737
    Prev
    Next
    INDEX
    Explanations

    New Balance

    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_3_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
    ා
    2.90
    ωσε
    2.62
    त्मक
    2.58
    ל
    2.57
    ूती
    2.56
    데요
    2.47
    waitKey
    2.44
    ु
    2.44
     giây
    2.41
    TIMESTAMP
    2.39
    POSITIVE LOGITS
     Encu
    2.32
    व
    2.31
     iya
    2.30
    tive
    2.29
    اب
    2.24
    usetts
    2.23
     dn
    2.16
     cioè
    2.12
    лу
    2.12
    ğı
    2.08
    Activations Density 0.001%

    No Known Activations