© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12676
    Prev
    Next
    INDEX
    Explanations

    young people, youth programs, stages of life

    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_13_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
     waste
    0.25
     .
    0.24
     diets
    0.24
     data
    0.23
    ात्
    0.22
     מד
    0.21
     workflow
    0.21
     P
    0.21
     कोशिकाओं
    0.21
     maps
    0.21
    POSITIVE LOGITS
     DBI
    0.22
    론
    0.22
    ഷേധ
    0.22
     penge
    0.21
    лардан
    0.21
     booted
    0.21
    elijk
    0.21
     objeto
    0.21
     الفاظ
    0.21
     ڈالر
    0.21
    Activations Density 0.004%

    No Known Activations