© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77698
    Prev
    Next
    INDEX
    Explanations

    formula definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    탔
    0.40
     opinião
    0.39
     efficaces
    0.38
    エスト
    0.38
     maravilh
    0.38
     schönsten
    0.37
    ﺼ
    0.37
     aonde
    0.37
     estilo
    0.37
    ᅬ
    0.36
    POSITIVE LOGITS
     Kindle
    0.40
    mb
    0.39
    nels
    0.39
     illustrated
    0.38
    master
    0.37
    vid
    0.36
    stead
    0.35
    规定
    0.35
     为了
    0.35
    规定的
    0.34
    Activations Density 0.000%

    No Known Activations