© 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. 122517
    Prev
    Next
    INDEX
    Explanations

    python code solution:

    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
    扑
    0.43
    cmake
    0.41
    ścia
    0.39
     TextInputLayout
    0.39
    Ethics
    0.36
     ലെ
    0.36
     benevolence
    0.36
    敵
    0.35
    ጀ
    0.35
    घे
    0.35
    POSITIVE LOGITS
     Ter
    0.46
     ter
    0.41
     Dalton
    0.38
     oversized
    0.35
    variants
    0.35
     جذاب
    0.34
     altitude
    0.34
    Ter
    0.34
     Glance
    0.34
    ter
    0.34
    Activations Density 0.001%

    No Known Activations