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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3687
    Prev
    Next
    INDEX
    Explanations

    OMG!

    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
    an
    2.04
    ჯგუფი
    1.79
    İlk
    1.78
    홧
    1.73
     necesitar
    1.71
    ﻤ
    1.71
     sebagainya
    1.69
     nutshell
    1.69
    ನ್ನಡ
    1.67
     Бушлай
    1.67
    POSITIVE LOGITS
    ل
    2.88
     hassle
    1.67
    эння
    1.62
    ীর
    1.60
    ित
    1.56
    тель
    1.56
    хи
    1.55
    ы
    1.54
    luxury
    1.53
    ли
    1.48
    Activations Density 0.001%

    No Known Activations