© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36320
    Prev
    Next
    INDEX
    Explanations

    samadhi

    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_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
    ر
    0.88
    л
    0.76
    ก
    0.72
    ม
    0.70
    ]
    0.68
    گزاری
    0.68
    0
    0.67
     aches
    0.67
     aplicativo
    0.64
    ть
    0.64
    POSITIVE LOGITS
    mě
    0.63
    ně
    0.62
    ᅴ
    0.62
     وأ
    0.59
    nungen
    0.58
    ভাবে
    0.57
     غير
    0.55
    <0x8E>
    0.54
    மாக
    0.54
     souten
    0.54
    Activations Density 0.003%

    No Known Activations