© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210834
    Prev
    Next
    INDEX
    Explanations

    budget approval

    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_20_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
    Consider
    0.30
     condizioni
    0.29
    えている
    0.28
     vých
    0.28
    0.28
    奏
    0.27
    0.27
     गेंद
    0.27
    وتی
    0.27
     ჩვენ
    0.26
    POSITIVE LOGITS
    鰱
    0.29
    лана
    0.28
     سکے
    0.28
     संग्रह
    0.28
     доход
    0.28
    পোর্ট
    0.28
    ᴙ
    0.27
     dissatisfied
    0.27
     lineNumber
    0.27
     پور
    0.27
    Activations Density 0.000%

    No Known Activations