© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199349
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    引起的
    0.40
    omonas
    0.39
    pop
    0.38
    娥
    0.37
    ورٹی
    0.37
    ociety
    0.37
    entum
    0.37
    orted
    0.36
    }}\\
    0.36
    joke
    0.36
    POSITIVE LOGITS
     affairs
    0.51
     Affairs
    0.47
     asuntos
    0.44
     mark
    0.42
     max
    0.41
     minis
    0.38
     affordability
    0.38
     min
    0.37
    ipset
    0.37
     maks
    0.36
    Activations Density 0.002%

    No Known Activations