© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202261
    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_12_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
    하는
    0.43
    casian
    0.39
    </u>
    0.39
     하는데
    0.39
     Burgund
    0.38
     Lubric
    0.38
     Kumb
    0.38
     Habsburg
    0.38
     하는
    0.37
    が増
    0.37
    POSITIVE LOGITS
     RECEIPTS
    0.39
    らい
    0.39
     televisión
    0.38
    ية
    0.38
    рія
    0.38
    VENUE
    0.38
     elicited
    0.37
    ة
    0.37
     МА
    0.37
    টেড
    0.36
    Activations Density 0.000%

    No Known Activations