© 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. 61529
    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
    1.09
    ために
    1.09
    行う
    1.06
     over
    1.04
    ))
    1.02
    ){
    0.97
     seminars
    0.96
    یت
    0.95
     неё
    0.94
     notre
    0.93
    POSITIVE LOGITS
    ра
    1.29
    ре
    1.19
    ని
    1.13
    c
    1.13
    ור
    1.07
    ри
    1.06
    리
    1.03
    ного
    1.02
    to
    1.00
    i
    0.95
    Activations Density 0.000%

    No Known Activations