© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233933
    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_46_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
    aconda
    0.37
     Col
    0.36
    );*/
    0.35
    廾
    0.34
     mise
    0.34
     mil
    0.34
     ملا
    0.34
    ويه
    0.34
    未
    0.33
     Cotton
    0.33
    POSITIVE LOGITS
    extras
    0.41
     హత్య
    0.40
    isterschaften
    0.38
    Grade
    0.38
    Uma
    0.37
    Tie
    0.37
     اجازت
    0.37
    Tuple
    0.37
     مک
    0.37
     Суриков
    0.37
    Activations Density 0.000%

    No Known Activations