© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 200081
    Prev
    Next
    INDEX
    Explanations

    plt.imshow function calls

    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_15_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
    ↵
    0.55
    <start_of_image>
    0.55
     warga
    0.52
     diving
    0.51
         
    0.51
    eta
    0.49
    riven
    0.49
     dive
    0.49
    atar
    0.48
     river
    0.48
    POSITIVE LOGITS
    인다
    0.60
    incu
    0.58
    인
    0.57
    блема
    0.57
     UpdateWindow
    0.57
     Evaluación
    0.56
    𝐵
    0.56
    кування
    0.56
    ᐋ
    0.56
    стка
    0.55
    Activations Density 0.001%

    No Known Activations