© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
     of
    1.21
    ン
    1.14
    ม
    1.08
    ন
    1.07
    은
    1.05
    이
    1.05
            
    1.02
     dite
    1.02
    や
    1.02
     cui
    0.98
    POSITIVE LOGITS
    and
    0.87
    ют
    0.83
    arse
    0.82
     возмо
    0.81
    arl
    0.80
    giving
    0.79
    gain
    0.79
    gäng
    0.78
     अच्छा
    0.78
    ра
    0.77
    Activations Density 0.000%

    No Known Activations