© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121465
    Prev
    Next
    INDEX
    Explanations

    note that

    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
    Negative Logits
     있는
    0.81
    ہ
    0.80
    ும்
    0.78
    ני
    0.76
    یت
    0.74
    ระหว่าง
    0.73
    ס
    0.71
     있다
    0.70
    یس
    0.70
    ۔
    0.70
    POSITIVE LOGITS
    note
    0.91
    don
    0.75
    d
    0.73
    notes
    0.73
    dag
    0.73
    r
    0.72
    did
    0.71
    a
    0.71
    পাতি
    0.70
    dür
    0.70
    Activations Density 0.001%

    No Known Activations