© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 203206
    Prev
    Next
    INDEX
    Explanations

    special characters"

    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
    ٰی
    0.39
    narr
    0.35
    धी
    0.35
    誦
    0.34
    {|
    0.34
     চীৎকার
    0.34
     precluded
    0.33
    bowtie
    0.33
     запуска
    0.33
    ึก
    0.32
    POSITIVE LOGITS
     माने
    0.46
     Gingerbread
    0.42
     Hutchinson
    0.38
     गर्
    0.37
     Elli
    0.36
    </strong>
    0.36
    Elli
    0.35
     የመ
    0.35
     mask
    0.35
     ang
    0.35
    Activations Density 0.002%

    No Known Activations