© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214685
    Prev
    Next
    INDEX
    Explanations

    skinned apples

    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_5_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
    วิธี
    0.92
    ↵
    0.91
    กัน
    0.86
    0.85
    วิธีการ
    0.83
    <0x80>
    0.81
     сообщи
    0.79
    ঁ
    0.77
    ก็
    0.77
    ุ
    0.76
    POSITIVE LOGITS
    ール
    1.25
    ב
    1.16
    ート
    1.14
    page
    1.06
    ia
    1.04
    ة
    1.02
    ര്‍
    1.02
    ü
    1.02
    pregn
    0.99
    prü
    0.98
    Activations Density 0.000%

    No Known Activations