© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    Saint- names

    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
    ा
    1.40
    끔
    1.36
    Shiv
    1.34
    ーブ
    1.32
    Ѕ
    1.32
     dragging
    1.31
    ỏng
    1.28
    गेटिव
    1.27
    sorting
    1.27
    lijke
    1.27
    POSITIVE LOGITS
    an
    1.95
    ب
    1.74
    ◦
    1.54
     Daarnaast
    1.51
    𝑐
    1.51
    ੀ
    1.46
    ين
    1.45
    ان
    1.45
    /−
    1.43
     anv
    1.42
    Activations Density 0.002%

    No Known Activations