© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60573
    Prev
    Next
    INDEX
    Explanations

    people or funding

    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_59_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
     Зна
    0.43
     drops
    0.38
    скі
    0.38
     Significant
    0.38
    atau
    0.38
    {:
    0.37
     breaks
    0.37
     significant
    0.36
    /(
    0.36
    /_
    0.36
    POSITIVE LOGITS
     people
    0.61
    people
    0.59
     людей
    0.58
     funding
    0.57
     Funding
    0.54
     emberek
    0.53
     mensen
    0.52
    funding
    0.52
     ludzi
    0.50
     ljudi
    0.50
    Activations Density 0.007%

    No Known Activations