© 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. 162072
    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
     integrable
    1.17
     susceptibles
    1.16
     і
    1.15
    ುದು
    1.15
    ினேன்
    1.12
     infringing
    1.09
    oirs
    1.09
     ако
    1.09
     annoyed
    1.08
    ۳
    1.08
    POSITIVE LOGITS
    OS
    1.38
    DA
    1.34
    MA
    1.28
    2
    1.28
    ž
    1.26
    á
    1.25
    า
    1.25
    1
    1.24
     that
    1.20
    ها
    1.20
    Activations Density 0.000%

    No Known Activations