© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112131
    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_2_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
    1
    1.37
    5
    1.21
    اً
    1.19
     to
    1.09
    ุ
    1.08
    0
    0.95
    این
    0.94
    ohm
    0.94
    6
    0.93
    />
    0.93
    POSITIVE LOGITS
    ن
    1.20
    ي
    1.04
     assur
    1.01
    رك
    0.97
     principes
    0.94
    -
    0.94
     institu
    0.92
    رة
    0.91
    ン
    0.90
     D
    0.89
    Activations Density 0.000%

    No Known Activations