© 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. 6126
    Prev
    Next
    INDEX
    Explanations

    code comments and structure separators

    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
    いない
    2.40
    ला
    2.24
    نا
    2.14
    ل
    1.99
    𝒂
    1.97
    ו
    1.96
    ுள்ளனர்
    1.94
    তিক্রম
    1.92
    𝒊
    1.92
    셋
    1.90
    POSITIVE LOGITS
    et
    2.14
    와이스
    2.09
     rearing
    2.05
     trimming
    2.03
    ]-\
    2.00
    кци
    1.95
    ch
    1.95
     pointers
    1.95
     Qxf
    1.92
    テーション
    1.92
    Activations Density 0.057%

    No Known Activations