© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51848
    Prev
    Next
    INDEX
    Explanations

    contact information, email, phone

    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_30_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
     provoque
    0.38
    del
    0.38
     указывает
    0.38
    徙
    0.37
    boomerang
    0.36
    ukhov
    0.36
    带来
    0.35
     Penguins
    0.35
    imos
    0.35
    嬋
    0.35
    POSITIVE LOGITS
     наша
    0.38
     মানুষ
    0.36
    नु
    0.36
     кеңсе
    0.35
    ೖ
    0.35
    ңү
    0.35
     %><%=
    0.35
     passionate
    0.34
    ണു
    0.33
    spers
    0.33
    Activations Density 0.000%

    No Known Activations