© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165083
    Prev
    Next
    INDEX
    Explanations

    stakeholder mapping

    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
     Lí
    0.50
    ভের
    0.49
     संख्याओं
    0.49
    ᚑ
    0.49
     Desenvolvimento
    0.48
    সভা
    0.47
    旂
    0.46
     wynik
    0.46
     jährlich
    0.46
     Фе
    0.45
    POSITIVE LOGITS
    k
    0.52
    :
    0.52
     :
    0.50
    www
    0.47
      
    0.46
    situation
    0.45
    t
    0.45
    mj
    0.44
    times
    0.44
    is
    0.44
    Activations Density 0.009%

    No Known Activations