© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5119
    Prev
    Next
    INDEX
    Explanations

    Sterogen, tablet, psychiatric side

    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_39_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
     भाग्य
    0.41
     VAT
    0.38
    äure
    0.38
     कर्मचारियों
    0.37
     şart
    0.37
     Employees
    0.37
    ╿
    0.37
     තු
    0.36
     sentimos
    0.36
    Employee
    0.36
    POSITIVE LOGITS
     gep
    0.38
     insp
    0.37
     =='
    0.37
     pomer
    0.36
     ged
    0.36
     worsening
    0.36
     suicidal
    0.35
     tablet
    0.35
     लिव
    0.35
    intent
    0.35
    Activations Density 0.067%

    No Known Activations