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

    Neuronpedia

    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. 132100
    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_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
    0
    1.36
    '
    1.09
    ’
    0.98
    1
    0.95
    2
    0.91
    to
    0.84
    ),
    0.81
    ↵↵
    0.78
    一
    0.78
    4
    0.75
    POSITIVE LOGITS
    dır
    0.96
    يت
    0.92
     شي
    0.92
    iyorum
    0.89
     Quindi
    0.88
    ди
    0.87
     غير
    0.84
     براي
    0.83
    드
    0.83
    áš
    0.82
    Activations Density 0.000%

    No Known Activations