© 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. 112303
    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
    스
    1.28
    ী
    1.18
    すぐに
    1.13
     liquidate
    1.12
     deduce
    1.09
    я
    1.09
    ް
    1.09
    ס
    1.09
     nè
    1.08
    tać
    1.08
    POSITIVE LOGITS
     الم
    1.09
     الع
    1.05
    lee
    1.05
    ag
    1.04
     it
    1.01
    h
    1.00
    out
    0.98
    lev
    0.97
    on
    0.96
    ings
    0.94
    Activations Density 0.000%

    No Known Activations