© 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. 58971
    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
    1.39
    3
    1.31
    我
    1.30
    6
    1.23
    م
    1.23
    这
    1.21
    ب
    1.20
    他
    1.20
    In
    1.16
    ك
    1.16
    POSITIVE LOGITS
    ag
    1.02
    t
    0.94
    en
    0.93
     chinois
    0.91
     originator
    0.91
     appliqué
    0.90
    एम
    0.88
     announcer
    0.88
     depender
    0.87
    ું
    0.85
    Activations Density 0.000%

    No Known Activations