© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232317
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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_32_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
    вичай
    0.37
    Fiction
    0.37
    갤럭
    0.36
     männ
    0.35
    Cro
    0.35
    之所以
    0.35
     मनाया
    0.34
     প্রতিষ্ঠার
    0.34
    阻
    0.34
    Hop
    0.34
    POSITIVE LOGITS
     reminder
    0.38
     CONS
    0.38
     ủng
    0.36
     trương
    0.36
     ransom
    0.36
     처
    0.35
    `](
    0.35
    wię
    0.34
    USART
    0.34
     derrière
    0.34
    Activations Density 0.000%

    No Known Activations