© 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. 124448
    Prev
    Next
    INDEX
    Explanations

    for, mechanisms, dialog, Stop

    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
    。
    0.91
    㵴
    0.59
    <td>
    0.55
    ágina
    0.55
    ských
    0.55
     ہے۔
    0.55
     tradition
    0.54
    క్షణ
    0.54
    OL
    0.54
    ۔
    0.54
    POSITIVE LOGITS
    یک
    0.87
    ин
    0.77
    education
    0.74
     allemand
    0.74
    이
    0.73
    ファ
    0.71
     accueillir
    0.70
    의
    0.70
    یر
    0.69
     avaient
    0.69
    Activations Density 0.000%

    No Known Activations