© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138581
    Prev
    Next
    INDEX
    Explanations

    `true` followed by `{` or `)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     एक्सप्लेन
    0.46
     ==
    0.40
    ]=="
    0.39
     checkpoint
    0.38
     perifer
    0.38
     सीन
    0.38
    চু
    0.37
    oconut
    0.37
    YSIS
    0.37
     പ്രതീക്ഷ
    0.37
    POSITIVE LOGITS
    陏
    0.37
    चलिए
    0.36
    आइए
    0.36
     أكبر
    0.35
     sadd
    0.34
     Let
    0.34
     shal
    0.34
    órias
    0.33
    ्ता
    0.33
    الحكم
    0.33
    Activations Density 0.000%

    No Known Activations