© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31502
    Prev
    Next
    INDEX
    Explanations

    causes completion

    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
    ഞ്ചി
    0.38
     pol
    0.35
     ناخد
    0.34
     প্রতিনিধিত্ব
    0.32
     შე
    0.32
    SHIFT
    0.32
    扇
    0.32
    给出
    0.31
     ಕಡಿ
    0.31
    BufOffset
    0.31
    POSITIVE LOGITS
     makes
    1.38
    Makes
    1.37
     menjadikan
    1.37
     membuatnya
    1.35
     Makes
    1.34
    makes
    1.32
     make
    1.23
     يجعل
    1.23
     جعل
    1.19
     maakt
    1.18
    Activations Density 0.166%

    No Known Activations