© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135272
    Prev
    Next
    INDEX
    Explanations

    limit a approaches

    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_37_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
    グラス
    0.46
     barge
    0.38
     ю
    0.37
     wickedness
    0.37
    芡
    0.36
     줄
    0.35
     ಹೋಗ
    0.35
     유
    0.35
    slate
    0.35
    リーグ
    0.35
    POSITIVE LOGITS
     تحفظ
    0.44
     protection
    0.41
     циф
    0.41
     Crimea
    0.40
    Protection
    0.40
     Protection
    0.39
    oulli
    0.38
     proteção
    0.38
    ओ
    0.38
    कृष्ण
    0.38
    Activations Density 0.003%

    No Known Activations