© 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. 4931
    Prev
    Next
    INDEX
    Explanations

    project file paths

    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
     ​​​​
    1.87
    े
    1.77
    𝖑
    1.71
    𝖒
    1.68
     hecho
    1.65
    en
    1.64
    ្យ
    1.61
     mellitus
    1.59
     ari
    1.58
     불구
    1.56
    POSITIVE LOGITS
    ل
    1.88
    androidTest
    1.70
    đ
    1.68
    resultSet
    1.66
    पाठ
    1.63
    ष्कार
    1.58
    ۜ
    1.57
    들
    1.54
    要
    1.47
    bí
    1.47
    Activations Density 0.010%

    No Known Activations