© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82726
    Prev
    Next
    INDEX
    Explanations

    play or roam

    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
     டீ
    0.40
    蠶
    0.40
     flu
    0.39
     jumps
    0.39
    rakk
    0.38
    কব
    0.38
    Vel
    0.37
    পাকিস্ত
    0.36
    ண்கள்
    0.36
    プライ
    0.36
    POSITIVE LOGITS
    游
    0.55
    遊
    0.46
    illé
    0.41
     roam
    0.39
    ার্স
    0.39
    試
    0.37
     গু
    0.36
     poser
    0.36
     Communism
    0.36
    试
    0.36
    Activations Density 0.002%

    No Known Activations