© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205752
    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
    k
    1.30
    نا
    1.23
    de
    1.20
    a
    1.11
    ни
    1.10
    d
    1.10
    l
    1.05
     a
    1.02
    ก
    1.02
    n
    1.01
    POSITIVE LOGITS
    1.31
     هي
    0.91
     الك
    0.89
     tedes
    0.88
     كتب
    0.87
     aşağıdaki
    0.87
     يك
    0.86
     وهي
    0.85
     يجب
    0.84
     nejsou
    0.84
    Activations Density 0.000%

    No Known Activations