© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81455
    Prev
    Next
    INDEX
    Explanations

    za

    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_53_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
    Voc
    0.41
    ansky
    0.41
    কোষ
    0.40
    শ
    0.39
    ходу
    0.39
     बृह
    0.39
     appelle
    0.38
    殼
    0.38
     TRS
    0.37
    шку
    0.37
    POSITIVE LOGITS
     zan
    0.48
     Zan
    0.44
    zan
    0.43
    contentText
    0.40
    zap
    0.39
     Zack
    0.37
    กว่า
    0.37
    Amanda
    0.37
     zal
    0.36
    টিল
    0.36
    Activations Density 0.001%

    No Known Activations