© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33907
    Prev
    Next
    INDEX
    Explanations

    Lanc/Lans

    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
     Kwan
    0.43
     taf
    0.39
    副
    0.37
    醍
    0.37
     Congrès
    0.36
     airways
    0.36
    ე
    0.36
     Gw
    0.36
     Cerv
    0.36
    AI
    0.36
    POSITIVE LOGITS
     পলিপ
    0.42
    тропо
    0.41
    チョコレート
    0.41
    ccccc
    0.40
    ヽ
    0.40
     dSample
    0.39
     Chocolate
    0.39
    Chocolate
    0.38
     പതി
    0.38
    chocolate
    0.38
    Activations Density 0.000%

    No Known Activations