© 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. 133317
    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
    ا
    1.03
    m
    0.94
    ot
    0.91
    t
    0.91
    p
    0.88
    اج
    0.87
    czyn
    0.84
    arh
    0.81
    uje
    0.80
    N
    0.79
    POSITIVE LOGITS
     tenté
    1.00
     that
    0.98
     of
    0.97
     markets
    0.95
     divides
    0.93
     profits
    0.91
     ຫຼື
    0.90
     bộ
    0.89
     breakfasts
    0.89
    ିକ
    0.88
    Activations Density 0.000%

    No Known Activations