© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27849
    Prev
    Next
    INDEX
    Explanations

    target value in two sum problems

    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_40_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
    蜻
    0.39
     رون
    0.39
     Ains
    0.35
    色彩
    0.35
    尼斯
    0.35
     Input
    0.34
    錫
    0.34
    <()>
    0.34
     настро
    0.34
    टन
    0.33
    POSITIVE LOGITS
    目标
    0.57
     target
    0.53
     targets
    0.50
     missed
    0.48
     cible
    0.48
    目標
    0.47
     целью
    0.45
     mục
    0.44
     цель
    0.44
     mål
    0.43
    Activations Density 0.003%

    No Known Activations