© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86759
    Prev
    Next
    INDEX
    Explanations

    division by zero protection

    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_23_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
    Communication
    0.45
     platform
    0.44
     gearbox
    0.43
     platoon
    0.42
     device
    0.42
    地
    0.42
    डा
    0.41
    Social
    0.40
    Life
    0.40
     taw
    0.40
    POSITIVE LOGITS
     улице
    0.39
     '*'
    0.38
     ఇదే
    0.38
    옌
    0.37
     StringIO
    0.37
    Carpenter
    0.36
    玧
    0.36
    प्रीत
    0.35
    σον
    0.35
     exon
    0.35
    Activations Density 0.002%

    No Known Activations