© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206158
    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_25_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
     involve
    0.39
    فاع
    0.37
     ultimately
    0.37
    Ultimately
    0.36
    Workbook
    0.36
     Ultimately
    0.35
    Eventually
    0.35
    ﹌
    0.35
    ory
    0.34
    稻
    0.34
    POSITIVE LOGITS
     yì
    0.44
     ڪرڻ
    0.41
     pat
    0.40
     FO
    0.39
     fez
    0.39
     coord
    0.39
     攵
    0.39
     lahat
    0.39
     SMTP
    0.38
     fontsize
    0.38
    Activations Density 0.000%

    No Known Activations