© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228517
    Prev
    Next
    INDEX
    Explanations

    improvisation or visual path

    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_6_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
    incredible
    0.98
    ın
    0.97
    ເຂ
    0.96
     в
    0.95
     और
    0.93
     και
    0.91
    ronics
    0.89
    ၅
    0.88
    am
    0.88
     и
    0.88
    POSITIVE LOGITS
    د
    1.47
    in
    1.04
    ]
    1.03
     or
    0.96
     to
    0.94
    ف
    0.88
     on
    0.88
    נה
    0.86
    อน
    0.85
     function
    0.83
    Activations Density 0.000%

    No Known Activations