© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50476
    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_31_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
    }^{-}\
    0.41
    借助
    0.38
     Brus
    0.38
    iladi
    0.38
    agul
    0.38
    Simple
    0.37
    ály
    0.36
    `<
    0.36
    browserTarget
    0.35
    पं
    0.35
    POSITIVE LOGITS
     integrations
    0.45
     troubleshoot
    0.41
     shaved
    0.40
     taut
    0.40
    tent
    0.38
     debunk
    0.38
     creatures
    0.37
     transducers
    0.37
     reinforcement
    0.37
    물이
    0.37
    Activations Density 0.000%

    No Known Activations