© 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. 165320
    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
    溢
    0.40
     pedest
    0.37
     hambre
    0.36
     pounding
    0.36
     hungry
    0.35
    ंकर
    0.35
     सच्चाई
    0.35
    稜
    0.35
     whats
    0.34
    POSITIVE LOGITS
     farewell
    0.56
     Goodbye
    0.55
     Farewell
    0.55
     goodbye
    0.54
    Goodbye
    0.53
    Bye
    0.50
    bye
    0.48
     বিদ
    0.45
     अलविदा
    0.43
    Depart
    0.42
    Activations Density 0.000%

    No Known Activations