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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174753
    Prev
    Next
    INDEX
    Explanations

    write text

    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_20_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
    结局
    0.38
    ！！！！
    0.37
     заявления
    0.37
     trabajado
    0.37
    Ἁ
    0.37
    шать
    0.36
    ।--
    0.36
    FILTER
    0.35
    힝
    0.35
    हो
    0.35
    POSITIVE LOGITS
     آئ
    0.40
     Nok
    0.40
     K
    0.40
     Brook
    0.39
     К
    0.38
     মসজিদের
    0.38
     Kn
    0.37
     Shoulder
    0.37
     Precision
    0.36
     Brooks
    0.36
    Activations Density 0.012%

    No Known Activations