© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81728
    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_0_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
    '
    1.56
    كم
    1.40
    لا
    1.38
    ير
    1.38
    מ
    1.38
    on
    1.35
    re
    1.34
    ۔
    1.31
    の間
    1.27
    س
    1.27
    POSITIVE LOGITS
    ита
    1.15
     genitalia
    1.04
    ofi
    1.02
     multimodal
    1.00
     та
    0.98
     в
    0.96
     tony
    0.96
    )}')
    0.96
     ito
    0.95
     pesa
    0.95
    Activations Density 0.000%

    No Known Activations