© 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. 163942
    Prev
    Next
    INDEX
    Explanations

    code comments `//` after punctuation

    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_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
     Oka
    0.38
    ត្រ
    0.35
    premier
    0.35
     ព
    0.35
    디오
    0.35
    Elizabeth
    0.34
     ಹೋಗ
    0.34
    计划
    0.34
     shu
    0.34
     maks
    0.33
    POSITIVE LOGITS
    孤
    0.42
     Cole
    0.39
    odb
    0.38
     Directive
    0.38
     discernment
    0.38
     inviol
    0.37
     calam
    0.36
    tuvo
    0.36
     Isolated
    0.36
     Kob
    0.35
    Activations Density 0.003%

    No Known Activations