© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8873
    Prev
    Next
    INDEX
    Explanations

    concept art and narrative scenes

    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_13_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
    लोकन
    0.52
    ď
    0.52
    да
    0.50
    ది
    0.49
    اید
    0.48
     hugs
    0.48
    ieť
    0.47
    docx
    0.47
    дяки
    0.47
    ையில்
    0.47
    POSITIVE LOGITS
     przest
    0.50
     カル
    0.50
     presenceData
    0.49
    කාර
    0.48
     Carpet
    0.47
    profit
    0.47
     militar
    0.47
    貳
    0.47
     dren
    0.46
    OUGHT
    0.46
    Activations Density 0.054%

    No Known Activations