© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201878
    Prev
    Next
    INDEX
    Explanations

    electric

    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_37_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
    pg
    0.42
     pode
    0.39
    inherit
    0.39
    unified
    0.39
    ilib
    0.38
    tg
    0.38
    ☼
    0.37
    އ
    0.37
     tgt
    0.36
     pg
    0.36
    POSITIVE LOGITS
     камеры
    0.41
    旋
    0.41
     বুদ্ধ
    0.41
     بوس
    0.41
    мости
    0.40
    专业
    0.39
     카메라
    0.38
    外的
    0.38
    技术
    0.37
     বস
    0.37
    Activations Density 0.001%

    No Known Activations