© 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. 205359
    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
     in
    0.98
     ***
    0.96
    ný
    0.91
     (__
    0.87
     في
    0.86
     >>>
    0.86
     ___
    0.86
     -
    0.85
     Sağ
    0.85
    í
    0.85
    POSITIVE LOGITS
    of
    1.43
    on
    1.21
    ین
    1.08
    ン
    0.99
    ک
    0.96
    oin
    0.89
    1
    0.89
    োর
    0.88
    وینت
    0.87
     editorials
    0.87
    Activations Density 0.000%

    No Known Activations