© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7493
    Prev
    Next
    INDEX
    Explanations

    Clarity

    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_39_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
    isimple
    0.42
    ﺢ
    0.39
     ски
    0.38
     zabezpie
    0.38
    abez
    0.38
     زود
    0.37
    ޗ
    0.36
    arza
    0.36
    ]=='
    0.36
    idbody
    0.36
    POSITIVE LOGITS
     클
    0.63
    클
    0.63
    クレ
    0.63
    Cl
    0.62
     Cl
    0.56
    ycl
    0.55
     ক্লা
    0.55
     кло
    0.54
     Cler
    0.54
    Clarke
    0.54
    Activations Density 0.063%

    No Known Activations