© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44775
    Prev
    Next
    INDEX
    Explanations

    non-english words greetings pauses

    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_22_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
    というのが
    0.42
     conjugates
    0.41
     कॉम
    0.40
     *(
    0.39
    だろう
    0.38
     irritating
    0.38
     conjug
    0.38
     imitated
    0.38
     Vx
    0.38
     copyright
    0.37
    POSITIVE LOGITS
    鹂
    0.40
    heva
    0.39
    adhyay
    0.38
    ña
    0.36
    Ƹ
    0.36
    点头
    0.35
    горе
    0.35
    鈞
    0.35
    跗
    0.35
    ểu
    0.34
    Activations Density 0.000%

    No Known Activations