© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194636
    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_27_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
    ጠር
    0.39
     inhabiting
    0.38
    暱
    0.37
     آگ
    0.36
    ாளர்களுக்கு
    0.35
     thirteenth
    0.35
    гия
    0.34
    ="<%=
    0.34
    赠
    0.34
    >$
    0.33
    POSITIVE LOGITS
    exam
    0.41
    हीर
    0.40
    리카
    0.39
     Datum
    0.39
     single
    0.39
    protractor
    0.38
     Connector
    0.38
     священ
    0.38
     ASSEM
    0.37
     teeth
    0.37
    Activations Density 0.000%

    No Known Activations